CN106096588A - The processing method of a kind of view data, device and mobile terminal - Google Patents

Abstract

Embodiments of the present invention provide an image data processing method, device, and mobile terminal. The method includes: acquiring original image data collected by a camera; identifying human body image data in the original image data; identifying human body image data in the human body image data Detecting skin color image data belonging to human body parts; setting a target skin color value for the human body part according to the characteristic information of the human body image data; performing normalization processing on the skin color image data according to the target skin color value, Obtain target image data. The embodiment of the present invention enables the input skin color to tend to or even reach the target skin color, solves the problem that the skin color is controlled by image processing, and the overall stability is poor, resulting in different performances of the skin color in various environments, and the output is stable and consistent. At the same time, the debugging cycle of image processing is shortened.

Description

Image data processing method, device and mobile terminal

technical field

The present invention relates to the technical field of communication, in particular to an image data processing method, an image data processing device and a mobile terminal.

Background technique

With the rapid development of mobile communication technology, mobile terminals such as mobile phones and tablet computers have been widely used in learning, entertainment, work, etc., and play an increasingly important role in people's daily life.

The mobile terminal is usually equipped with a camera, and because the mobile terminal is more convenient to carry than the camera, many users are accustomed to using the mobile terminal to take pictures.

In situations such as self-portraits and group photos, users will take photos of people. Since various image processing will be performed during the photo-taking process, the debugging cycle of these image processing is long. At the same time, the skin color is also controlled by image processing, and the overall stability is poor. Causes skin color to behave differently in various environments.

Contents of the invention

In view of the above problems, the present invention is proposed to provide an image data processing method, a corresponding image data processing device, and a mobile terminal that overcome the above problems or at least partially solve the above problems.

In a first aspect, an embodiment of the present invention provides a method for processing image data, including:

Obtain the original image data collected by the camera;

identifying human body image data in the raw image data;

Detecting skin color image data belonging to human body parts in the human body image data;

setting a target skin color value for the human body part according to the characteristic information of the human body image data;

performing normalization processing on the skin color image data according to the target skin color value to obtain target image data.

In a second aspect, an image data processing device is provided in an embodiment of the present invention, including:

The original image data acquisition module is used to obtain the original image data collected by the camera;

A human body image data identification module, configured to identify the human body image data in the original image data;

A skin color image data detection module, configured to detect skin color image data belonging to human body parts in the human body image data;

A target skin color value setting module, configured to set a target skin color value for the human body part according to the characteristic information of the human body image data;

A normalization processing module, configured to perform normalization processing on the skin color image data according to the target skin color value to obtain target image data.

In a third aspect, an embodiment of the present invention provides a mobile terminal, where the mobile terminal has a function of implementing the image data processing behavior in the above first aspect. The functions described above may be implemented by hardware, or may be implemented by executing corresponding software on the hardware. The hardware or software includes one or more modules corresponding to the above functions.

In a possible design, the structure of the mobile terminal includes a processor and a memory, the memory is used to store a program that supports the transceiver device to execute the above method, and the processor is configured to execute the program stored in the memory . The mobile terminal may also include a communication interface for the mobile terminal to communicate with other devices or a communication network.

Wherein, the memory is used to store the instruction for acquiring the original image data collected by the camera, the instruction for identifying the human body image data in the original image data, and the detection of the skin color image data belonging to the human body parts in the human body image data An instruction, an instruction of setting a target skin color value for the human body part according to the characteristic information of the human body image data, performing normalization processing on the skin color image data according to the target skin color value, and obtaining an instruction of the target image data;

The processor is used to:

Acquire the original image data collected by the camera according to the instruction for obtaining the original image data collected by the camera;

identifying human body image data in the original image data according to the instruction for identifying human body image data in the original image data;

According to the instruction of detecting skin color image data belonging to human body parts in the human body image data, detecting skin color image data belonging to human body parts in the human body image data;

According to the instruction of setting a target skin color value for the human body part according to the characteristic information of the human body image data, set a target skin color value for the human body part according to the characteristic information of the human body image data;

According to the instruction of normalizing the skin color image data according to the target skin color value to obtain the target image data, normalizing the skin color image data according to the target skin color value to obtain the target image data.

According to the solution provided by the present invention, the user can use the mobile terminal to obtain the original image data collected by the camera, identify the human body image data from the original image data, and then detect the destination and the skin color image data of the human body parts, and analyze the human body based on the characteristic information of the human body image data. The target skin color value is set in the part, and the skin color image data is normalized according to the target skin color value to obtain the target image data, so that the input skin color can tend to or even reach the target skin color, and the skin color is controlled by image processing. The overall stability is poor, which leads to the problem that skin color behaves differently in various environments, and the output is stable and consistent skin color. At the same time, the debugging cycle of image processing is shortened.

These or other aspects of the present invention will be more clearly understood in the description of the following embodiments.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a flow chart of the steps of an embodiment of a method for processing image data according to an embodiment of the present invention;

FIG. 2 shows a flow chart of the steps of another image data processing method embodiment according to an embodiment of the present invention;

Fig. 3 shows a structural block diagram of an embodiment of an image data processing device according to an embodiment of the present invention;

FIG. 4 shows a structural block diagram of another image data processing device embodiment according to an embodiment of the present invention; and

Fig. 5 shows a block diagram of a partial structure of a mobile phone related to a mobile terminal according to an embodiment of the present invention.

detailed description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Referring to FIG. 1 , it shows a flow chart of the steps of an embodiment of a method for processing image data according to an embodiment of the present invention, which may specifically include the following steps:

Step 101, acquire raw image data collected by a camera.

In a specific implementation, the embodiments of the present invention can be applied in mobile terminals, for example, mobile phones, tablet computers, personal digital assistants, wearable devices (such as glasses, watches, etc.) and the like.

The operating systems of these mobile terminals may include Android (Android), IOS, Windows Phone, Windows, and the like.

In the embodiment of the present invention, a camera may be configured in the mobile terminal.

These cameras can be configured on the front of the mobile terminal (also known as the front camera), and can also be configured on the back of the mobile terminal (also known as the rear camera). In addition, the number of the cameras can be single, or two or There are more than two cameras, such as dual cameras, etc., which is not limited in this embodiment of the present invention.

In an example, the camera may include components such as a lens, a base Holder, an infrared filter IR, an image sensing processor Sensor, and a circuit board.

Among them, the image sensing processor Sensor is a semiconductor chip, and its surface contains photodiodes ranging from hundreds of thousands to several million. When the photodiodes are irradiated by light, they can generate charges.

The image sensing processor Sensor can convert light into an electrical signal, and then convert it into a digital signal through the internal DA (digital-to-analog conversion). The plane where the image sensing processor Sensor is located is the imaging plane of the image data.

In practical applications, the optical image generated by the scene (SCENE) through the lens Lens of the camera is projected onto the surface of the image sensor processor Sensor, and then converted into an electrical signal, and then converted into a digital image signal by A/D (analog-to-digital conversion) , the digital image signal is compressed and converted into a specific image file format by the digital signal processing chip DSP or an encoding library, and is transmitted to the processor (Central Processing Unit, CPU) of the mobile terminal through the data bus for processing, then it can be processed on the mobile terminal The terminal screen is displayed.

Step 102, identifying human body image data in the original image data.

The so-called human body image data refers to image data representing a person in the original image data.

In scenarios such as self-portraits, one person is generally photographed, so one human body image data can be identified in the original image data; Identify multiple human body image data.

In a specific implementation, human body image data may be detected in one or more of the following ways:

1. Template or contour-based detection methods

Template or contour-based detection methods mainly use template matching and template classification methods to detect human body image data.

In one example, the contour features of the human body can be used in the template matching process at different levels to select candidate targets, and the shape appearance that the human body usually presents is used as the human target template, and the shape matching method based on distance transformation is used for matching from coarse to fine . Then, radial basis functions are used to validate the candidate targets.

2. Detection method based on motion information

The detection method based on motion information uses the periodicity of human motion to detect people in image data, and is generally suitable for detecting moving pedestrians.

In one example, a person is recognized from an image sequence by using the periodic movement characteristics of the legs when a person walks. First, the image data is divided into sub-image data and the pixels are clustered, and then the corresponding sub-image data are matched in the continuous image data. Classes and track various types, based on the time changes of class-like features, use fast polynomial classifier estimation to initially select the classes that may belong to human legs, and finally use the neural network to train the extracted classes that belong to legs, so as to judge whether there are people.

3. Detection method based on sliding window

The detection method based on the sliding window searches through the fixed-size detection window slidingly in the image data, and these windows are classified into two types by the classifier: people and people.

In one example, the sliding window detection method can be divided into two stages, the first stage is a training stage, and the second stage is a detection stage.

In the training phase, the training samples are first established, including positive samples and negative samples. The positive samples are the image areas that include the human body, and the negative samples are the image areas that do not include the human body. Features are then extracted from the positive and negative samples, which are generally represented in the form of feature vectors. Finally, a classifier is trained, which is used to distinguish the feature vectors of positive samples from the feature vectors of negative samples.

In the detection stage, since the size of the person in the image data is uncertain, and the size of the sliding window is generally fixed, in order to allow both small-scale people and large-scale people to be detected, an image with detected image data can be created Pyramid, use a fixed-size sliding window to slide on each level of the pyramid, and input the image features extracted in this window into the classifier for classification every time it slides to a position. The classifier outputs information about whether this window contains a person. When all positions and levels have been scanned by the sliding window, the person detected by the windows with similar positions in each level is likely to be the same person. In order to determine the final position of the human body, window fusion is performed to merge adjacent windows into one window.

4. Detection method based on part or local shape

Methods based on inanimate or partial shape rely on detecting the inanimate or partial shape of the human body, and then combine these features to determine the final human body position according to the geometric constraints of the human body model.

Certainly, the above-mentioned human body detection is only an example, and other human body detections may be set according to actual conditions when implementing the embodiment of the present invention, which is not limited in the embodiment of the present invention. In addition, in addition to the above human body detection, those skilled in the art may also use other human body detection according to actual needs, which is not limited in the embodiment of the present invention.

Step 103, detecting skin color image data belonging to human body parts in the human body image data.

In a specific implementation, a human body includes multiple parts, such as a face, a head, an arm, a calf, and the like.

When taking a photo, parts of the skin of these body parts are usually exposed and directly displayed in the image data, for example, when a user takes a selfie, the face usually occupies a large area.

Therefore, in the embodiment of the present invention, the part image data where the part of the human body is located can be detected in the human body image data by means of HOG (Histogram of Oriented Gradient, histogram of oriented gradient) algorithm, depth image learning, etc. Skin color detection to obtain skin color image data.

Taking the face as an example, the face detection can be performed in the original image data to obtain the face image data, and the skin color image data can be identified in the face image data.

The so-called face detection can refer to the position and size of the face from the image data.

In Android, a method of directly performing face detection on a bitmap is provided, and the two APIs (Application Programming Interface, application programming interface) are android.media.FaceDetector and android.media.FaceDetector.Face respectively.

Specifically, the base class ImageView is extended to become MyImageView, and the bitmap file containing the face to be detected is generally in 565 format to ensure the normal operation of the API.

The detected face needs a confidence measure, which is defined in android.media.FaceDetector.Face.CONFIDENCE_THRESHOLD.

Among them, setFace() can instantiate the FaceDetector object, call findFaces at the same time, store the result in faces, and transfer the midpoint of the face to MyImageView.

Next, add the setDisplayPoints() method in MyImageView to mark the detected faces for rendering.

While the API returns other useful information, for example, eyesDistance, pose, and confidence will be returned at the same time, and the center of the eyes can be located by eyesDistance.

The so-called skin color detection is the process of selecting pixels corresponding to human skin in the image data.

According to whether the imaging process is involved, skin color detection can be divided into the following two types:

1. Statistics-based skin color detection

The main steps of statistics-based skin color detection include color space transformation and skin color modeling.

Choosing the color space itself is choosing the most basic feature representation for skin color detection. Skin color modeling is a computer representation of skin color knowledge. Usually, a skin color model is established through a training sample set for skin color detection. According to different applications, skin color modeling can be divided into static and dynamic categories.

Among them, for the color space, the distribution of skin color in the color space is quite concentrated, but it will be greatly affected by lighting and race. In order to reduce the impact of skin color on lighting intensity, the color space is usually converted from RGB to a certain classification of brightness and chroma. a color space, such as YCbCr or HSV, and then discard brightness.

For static skin color modeling, the skin color model can be established by means of skin color range, Gaussian density function estimation and histogram statistics, which correspond to thresholding, parametric and non-parametric methods respectively.

For dynamic skin color modeling, the skin color model can be established by adjusting the parameters of the skin color model to adapt to a certain static image, or for sequence images, which can adapt to changes in imaging conditions over time.

2. Physically based skin color detection

Under complex lighting conditions, such as the skin color in the image in the highlight area or shadow area, in order to overcome the irrelevant influence of light on the image from the imaging mechanism, the interaction between light and skin and the pop characteristics of the skin should be considered when detecting skin color , this kind of skin color detection technology that considers the physical interaction between electromagnetic radiation and skin is called physically-based skin color detection.

In a physically-based skin color detection method, skin color detection can be performed through a physical model of skin reflection. For example, a two-color reflection model can simulate the reflection process of an opaque non-uniform dielectric object according to the reflection characteristics of the non-uniform dielectric for skin color detection. .

Of course, the above part detection and skin color detection are just examples. When implementing the embodiment of the present invention, other part detection and skin color detection can be set according to the actual situation, which is not limited in the embodiment of the present invention. In addition, in addition to the above part detection and skin color detection, those skilled in the art may also use other part detection and skin color detection according to actual needs, which is not limited in the embodiment of the present invention.

Step 104, setting a target skin color value for the human body part according to the characteristic information of the human body image data.

In practical applications, the skin color of people with different characteristics generally has different characteristics.

For example, the skin color of yellow people is generally yellowish, the skin color of white people is generally white, and the skin color of black people is generally dark.

For another example, for people of the yellow race, the color of the skin color will generally gradually deepen from the stages of childhood, juvenile, youth, middle age, and old age.

For another example, for the yellow race, the skin color of men is generally darker than that of women.

In addition, different body parts of these people have slightly different skin colors. For example, for people of yellow race, the skin color of women's faces is usually lighter than that of their arms.

Taking the RGB color space as an example, in the target skin color value, the R (red) value is generally greater than the G (green) value, and the G (green) value is generally greater than the B (blue) value. For example, the target skin color value corresponding to old age is (215 , 177, 141), the target skin color value corresponding to the middle age is (249, 217, 204), the target skin color value corresponding to the teenager is (253, 227, 204) and so on.

Therefore, for parts of people with different characteristics, the target skin color value can be set, and the mapping relationship between the person's feature information, human body parts and the target skin color value can be established.

After detecting the part image data where the human body part is located in the human body image data, the target skin color value corresponding to the human body part can be queried according to the mapping relationship.

In an example, one or more characteristic information of age information, gender information, and race information of the human body image data may be identified.

Query the target skin color value corresponding to the human body part based on one or more characteristic information in age information, gender information, and race information.

Of course, the above feature information is only an example, and other feature information may be set according to actual conditions when implementing the embodiment of the present invention, which is not limited in the embodiment of the present invention. In addition, in addition to the above feature information, those skilled in the art may also use other feature information according to actual needs, which is not limited in this embodiment of the present invention.

Step 105: Perform normalization processing on the skin color image data according to the target skin color value to obtain target image data.

By performing normalization processing on the target skin color value and the skin color image data, the skin color of the input skin color image data can be tended to or even reach the target skin color value, and a stable and consistent skin color can be output.

In practical applications, the characteristic skin color image data can be selected from the skin color image data through certain selection rules; the characteristic skin color image data can be normalized according to the target skin color value to obtain the target image data.

For example, characteristic skin color image data can be selected according to brightness and/or exposure, some skin color image data with uneven brightness and overexposure can be screened out, and skin color image data with uniform brightness and no overexposure can be retained.

Specifically, the brightness and/or exposure of the skin color image data may be counted by means of histogram statistics or the like.

Select image data whose brightness is within a preset brightness range and/or whose exposure is less than a preset exposure threshold from the skin color image data as characteristic skin color image data.

Of course, in addition to selecting part of the skin color image data for normalization processing, it is also possible to perform normalization processing for all skin color image data, which is not limited in this embodiment of the present invention.

In one embodiment of the present invention, step 105 may include the following sub-steps:

Sub-step S11, for each part image data, count the original skin color value in the part image data;

In a specific implementation, the pixel color values, such as RGB values, of each pixel in the skin color image data can be obtained, and the average value of the pixel color values can be calculated as the original skin color value.

Sub-step S12, using the original skin color value and the target skin color value to calculate a normalization coefficient;

In a specific implementation, the normalization coefficient may be calculated based on the calculated target skin color value, so as to adjust the original skin color value.

In an example of an embodiment of the present invention, substep S12 may include the following substeps:

Sub-step S121, calculating the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio;

Taking the RGB color space as an example, assuming that the target skin color value is (R _sample , G _sample , B _sample ), and the original skin color value of the skin color image data input by the camera is (R _input , G _input , B _input ), then the color The adjustment ratio is (R _ratio , G _ratio , B _ratio ):

R _ratio =R _sample /R _input

G _ratio = G _sample /G _input

B _ratio ＝B _sample /B _input

Sub-step S122: Multiply the pixel color value of each pixel in the skin color image data by the adjustment ratio to obtain a set of pixel color values.

Sub-step S123, selecting the target pixel color value from the pixel color value set.

In a specific implementation, the pixel color value with the largest value may be selected from the set of pixel color values as the target pixel color value.

Of course, in addition to selecting the pixel color value with the largest value, other pixel color values may also be selected as the target pixel color value, which is not limited in this embodiment of the present invention.

Taking the RGB color space as an example, assuming that the adjustment ratio is (R _ratio , G _ratio , B _ratio ), then multiply (R _ratio , G _ratio , B _ratio ) with each pixel of the skin color image data to obtain R _{( 0,1,2,...,n)} , G _{(0,1,2,...,.n)} , B _{(0,1,2,...,n)} , where n is an integer.

Statistics R (0, 1, 2, ... n), G (0, 1, 2, ... n), B (0, 1, 2, ... n) in the maximum RGB _max as the target pixel color value.

Sub-step S124, using the color adjustment ratio and the target pixel color value to calculate a normalization coefficient.

In a specific implementation, the ratio between the preset color threshold and the target pixel color value may be calculated as the pixel color ratio, and the product of the color adjustment ratio and the pixel color ratio may be calculated to obtain a normalization coefficient.

Taking the RGB color space as an example, assuming that the adjustment ratio is (R _ratio , G _ratio , B _ratio ) and the target pixel color value is RGB _max , the normalization coefficient is:

R _ratio *255/RGB _max

G _ratio *255/RGB _max

B _ratio *255/RGB _max

Sub-step S13, adjusting on the basis of the original skin color value with the normalization coefficient to obtain a normalized skin color value;

Sub-step S14, in the original image data, adjust the skin color image data with the normalized skin color value to obtain target image data.

In the embodiment of the present invention, the original skin color value can be adjusted according to the normalization coefficient to output the normalized skin color value.

Taking the RGB color space as an example, assume that the original skin color value is (R _input , G _input , B _input ), and the normalization coefficient is (R _ratio *255/RGB _max , G _ratio *255/RGB _max , B _ratio *255 /RGB _max ), then the output normalized skin color value (R _final , G _final , B _final ) is:

R _final =R _input *R _ratio *255/RGB _max ;

G _final = G _input *G _ratio *255/RGB _max ;

B _final = B _input *B _ratio *255/RGB _max ;

At present, in the camera module of the mobile terminal, after the AEC (Automatic Exposure Control, automatic exposure control) and AWB (Automatic white balance, automatic white balance) are stabilized, the exposure index (index) value of the AEC and the AWB output Color temperature value (CCT), to dynamically calculate the color restoration (colorcorrection) and saturation (color enhancement) parameters that should be used in the current scene.

This creates problems, for example, at different angles, different exposures, and different AWB outputs, even if the difference in AWB is not large, the final color reproduction and saturation parameters used will be inconsistent, resulting in inconsistent skin color in the image, even if It is tested by the same person, and the skin color difference is relatively large under different angles and different light sources.

At the same time, the screens of mobile terminals with different color temperatures (warm color screens, cool color screens, etc.) display different forms.

Therefore, the user experience is extremely bad, and at the same time, the existing adjustable parameters and debugging methods have a very long debugging cycle, and it is difficult to achieve the desired effect.

According to the solution provided by the present invention, the user can use the mobile terminal to obtain the original image data collected by the camera, identify the human body image data from the original image data, and then detect the destination and the skin color image data of the human body parts, and analyze the human body based on the characteristic information of the human body image data. The target skin color value is set in the part, and the skin color image data is normalized according to the target skin color value to obtain the target image data, so that the input skin color can tend to or even reach the target skin color, and the skin color is controlled by image processing. The overall stability is poor, which leads to the problem that skin color behaves differently in various environments, and the output is stable and consistent skin color. At the same time, the debugging cycle of image processing is shortened.

Referring to FIG. 2 , it shows a flow chart of the steps of an embodiment of a method for processing image data according to an embodiment of the present invention, which may specifically include the following steps:

Step 201, acquire raw image data collected by a camera.

Step 202, performing image processing on the original image data.

In the embodiment of the present invention, if the image data is collected by the camera, ISP (Image Signal Processing, image signal processing) processing may be performed.

Wherein, image processing includes at least one of the following:

1. Automatic Exposure Control

Exposure is a physical quantity used to calculate the luminous flux from the scene to the camera. The image sensor can only get high-quality photos if it gets the correct exposure. Overexpose and the image looks too bright Underexpose and the image looks too dark. The amount of luminous flux reaching the sensor is mainly determined by two factors: the length of exposure time and the size of the aperture.

The aperture is used for automatic exposure, and the size of the aperture is mainly controlled according to the scene being shot, so that the amount of light entering is maintained within a certain range. The cost of exposure control through the aperture is relatively high.

There are usually two methods of automatic exposure control algorithm:

One method is to use a reference brightness value to evenly divide the image into many sub-images, and the brightness of each sub-image is used to set a reference brightness value, which can be obtained by setting the shutter speed.

Another method is to control exposure by studying the relationship between brightness and exposure value under different lighting conditions.

2. White balance adjustment

White balance can also be understood as under any color temperature condition, the standard white captured by the camera is adjusted by the circuit so that it is still white after imaging.

Automatic white balance is based on the assumption that the average value of the color of the scene falls within a specific range. If the measured result deviates from this range, the corresponding parameters will be adjusted until the average value falls within the specified range. The processing may be based on YUV space or RGB space. For Sensor, the usual processing method is to correct the R/B gain so that the UV value falls within a specified range. This enables automatic white balance.

3. Color restoration processing

The human eye's recognition of color is based on the principle that the human eye has three different sensing units for light, and different sensing units have different response curves to different bands of light. The perception of color is obtained through the synthesis of the brain. Generally speaking, the concept of RGB three primary colors can be used to understand the decomposition and synthesis of colors.

Theoretically, if the human eye and sensor (sensor) respond to the color light of the spectrum, if it is reflected in the spectrum, basically the response to the three color lights will not affect each other, and there is no so-called cross effect. However, the actual situation is not so ideal. The response of the three-color sensing system of the human eye to the spectrum is that the response of RGB is not completely independent.

There is usually a deviation between the RGB components and the human eye's response to the spectrum, and of course it needs to be corrected. Not only the cross effect, but also the response intensity of each color component needs to be corrected. The usual method is to correct the color once through a color correction matrix.

The color correction operation is usually completed by the sensor module integration or the back-end ISP, and the correct correction result can be obtained by modifying the relevant registers. Among them, since the conversion of the color space from RGB to YUV is also realized through a 3*3 transformation matrix, sometimes these two matrices will be merged together in the process of ISP processing, and the color transformation can be completed through one matrix operation. Correction and conversion of color spaces.

4. Color enhancement processing

In a specific implementation, the color performance of the image data may be enhanced by adjusting saturation and the like.

The so-called saturation actually refers to the purity of the color. The higher the purity, the brighter the performance, and the lower the purity, the duller the performance.

Since each pixel of the liquid crystal is composed of red, green, and blue (RGB) sub-pixels, the backlight passes through the liquid crystal molecules and relies on the RGB pixels to combine into light of any color. The more vivid the RGB primary colors, the wider the range of colors that the display can represent. If the three primary colors of the display are not bright, the color range that the display can display is relatively narrow, because it cannot display more vivid colors than the three primary colors. Therefore, the way to increase color saturation is to increase the purity of the backlight spectrum and the three primary colors.

5. Denoising processing

During the acquisition and transmission of image data, the quality of image data is often affected by various noises and degrades.

For example, noise pollution when the image sensor acquires image data, due to the small amount of data at this time, the noise directly affects the subsequent interpolation algorithm, and makes the details of the image unable to be reflected, which not only affects the interpolation effect of the image, but also affects human vision feel.

Therefore, the removal of noise is a very important link in image processing.

The way of denoising processing is usually to take the mean value of the surrounding points to replace the original value. This method does not increase the amount of information, similar to a fuzzy algorithm.

During detection, the noise can be judged by combining the brightness and color as the standard, and the interpolation algorithm can be used for compensation. For the inherent bad pixels and noise of the sensor, the data can be discarded by masking and so on.

Of course, the above image processing is only an example. When implementing the embodiment of the present invention, other image processing, such as flicker suppression, may be set according to the actual situation, which is not limited in the embodiment of the present invention. In addition, in addition to the above image processing, those skilled in the art may also use other image processing according to actual needs, which is not limited in this embodiment of the present invention.

Step 203, identifying human body image data in the original image data.

Step 204, detecting skin color image data belonging to human body parts in the human body image data.

Step 205, setting a target skin color value for the human body part according to the characteristic information of the human body image data.

Step 206: Perform normalization processing on the skin color image data according to the target skin color value to obtain target image data.

In the embodiment of the present invention, the human body image data can be identified from the original image data after image processing, the target skin color value is set for human body parts according to the feature information of the human body image data after image processing, and the image is processed according to the target skin color value. Then the skin color image data is normalized to obtain the target image data.

For the method embodiment, for the sake of simple description, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiment of the present invention is not limited by the described action order, because according to the embodiment of the present invention , certain steps may be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

Referring to FIG. 3 , it shows a structural block diagram of an embodiment of an image data processing device according to an embodiment of the present invention, which may specifically include the following modules:

Raw image data acquisition module 301, used to acquire the original image data collected by the camera;

A human body image data identification module 302, configured to identify the human body image data in the original image data;

A skin color image data detection module 303, configured to detect skin color image data belonging to human body parts in the human body image data;

A target skin color value setting module 304, configured to set a target skin color value for the human body part according to the characteristic information of the human body image data;

A normalization processing module 305, configured to perform normalization processing on the skin color image data according to the target skin color value to obtain target image data.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

Selecting characteristic skin color image data in the skin color image data;

Perform normalization processing on the characteristic skin color image data according to the target skin color value to obtain target image data.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

Count the brightness and/or exposure of the skin color image data;

Select image data whose brightness is within a preset brightness range and/or whose exposure is less than a preset exposure threshold from the skin color image data as characteristic skin color image data.

In one embodiment of the present invention, the target skin color value setting module 304 can also be used for:

Identifying one or more characteristic information in the age information, gender information, and race information of the human body image data;

Query the target skin color value corresponding to the human body part based on one or more characteristic information in age information, gender information, and race information.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

For each skin color image data, count the original skin color value in the part image data;

calculating a normalization coefficient by using the original skin color value and the target skin color value;

On the basis of the original skin color value, adjust with the normalization coefficient to obtain a normalized skin color value;

In the original image data, the skin color image data is adjusted with the normalized skin color value to obtain target image data.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

Obtain the pixel color value of each pixel in the skin color image data;

Calculate the average value of the pixel color values as the original skin color value.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

calculating the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio;

multiplying the pixel color value of each pixel in the part image data by the adjustment ratio to obtain a set of pixel color values;

selecting a target pixel color value from the set of pixel color values;

A normalization coefficient is calculated by using the color adjustment ratio and the target pixel color value.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

From the set of pixel color values, select the pixel color value with the largest value as the target pixel color value.

In one embodiment of the present invention, the normalization processing module 305 can also be used for:

calculating the ratio between the preset color threshold and the target pixel color value as the pixel color ratio;

Calculate the product of the color adjustment ratio and the pixel color ratio to obtain a normalization coefficient.

Referring to FIG. 4 , it shows a structural block diagram of another image data processing device embodiment according to an embodiment of the present invention, which may specifically include the following modules:

Raw image data acquisition module 401, used to acquire the original image data collected by the camera;

An image processing module 402, configured to perform image processing on the original image data;

A human body image data identification module 403, configured to identify the human body image data in the original image data;

A skin color image data detection module 404, configured to detect skin color image data belonging to human body parts in the human body image data;

A target skin color value setting module 405, configured to set a target skin color value for the human body part according to the characteristic information of the human body image data;

A normalization processing module 406, configured to perform normalization processing on the skin color image data according to the target skin color value to obtain target image data.

In a specific implementation, the image processing includes at least one of the following:

Automatic exposure control, white balance adjustment, color restoration processing, color enhancement processing, denoising processing.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The embodiment of the present invention also provides a mobile terminal. As shown in FIG. 5 , for convenience of description, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The terminal can be any terminal device including mobile phone, tablet computer, PDA (Personal Digital Assistant, personal digital assistant), POS (Point of Sales, sales terminal), vehicle-mounted computer, etc. Taking the terminal as a mobile phone as an example:

FIG. 5 shows a block diagram of a partial structure of a mobile phone related to a terminal provided by an embodiment of the present invention. 5, the mobile phone includes: a radio frequency (Radio Frequency, RF) circuit 510, a memory 520, an input unit 530, a display unit 540, a sensor 550, an audio circuit 560, a wireless fidelity (wireless fidelity, WiFi) module 570, a processor 580 , and power supply 590 and other components. Those skilled in the art can understand that the structure of the mobile phone shown in FIG. 5 is not limited to the mobile phone, and may include more or less components than shown in the figure, or combine some components, or arrange different components.

The following is a specific introduction to each component of the mobile phone in conjunction with Figure 5:

The RF circuit 510 can be used for sending and receiving information or receiving and sending signals during a call. In particular, after receiving the downlink information from the base station, the processor 580 processes it; in addition, it sends the designed uplink data to the base station. Generally, the RF circuit 510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, and the like. In addition, RF circuitry 510 may also communicate with networks and other devices via wireless communications. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access) , CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (Short Messaging Service, SMS), etc.

The memory 520 can be used to store software programs and modules, and the processor 580 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 520 . The memory 520 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of mobile phones (such as audio data, phonebook, etc.), etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The input unit 530 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the mobile phone. Specifically, the input unit 530 may include a touch panel 531 and other input devices 532 . The touch panel 531, also referred to as a touch screen, can collect touch operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger or a stylus on the touch panel 531 or near the touch panel 531). operation), and drive the corresponding connection device according to the preset program. Optionally, the touch panel 531 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and sends it to the to the processor 580, and can receive and execute commands sent by the processor 580. In addition, the touch panel 531 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 531 , the input unit 530 may also include other input devices 532 . Specifically, other input devices 532 may include but not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), trackball, mouse, joystick, and the like.

The display unit 540 may be used to display information input by or provided to the user and various menus of the mobile phone. The display unit 540 may include a display panel 541. Optionally, the display panel 541 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like. Further, the touch panel 531 may cover the display panel 541, and when the touch panel 531 detects a touch operation on or near it, it transmits to the processor 580 to determine the type of the touch event, and then the processor 580 determines the type of the touch event according to the touch event. The type provides a corresponding visual output on the display panel 541 . Although in FIG. 5 , the touch panel 531 and the display panel 541 are used as two independent components to realize the input and input functions of the mobile phone, in some embodiments, the touch panel 531 and the display panel 541 can be integrated to form a mobile phone. Realize the input and output functions of the mobile phone.

The handset may also include at least one sensor 550, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor can include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 541 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 541 and/or when the mobile phone is moved to the ear. or backlight. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is stationary, and can be used to identify the application of mobile phone posture (such as horizontal and vertical screen switching, related Games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tap), etc.; as for other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. repeat.

The audio circuit 560, the speaker 561, and the microphone 562 can provide an audio interface between the user and the mobile phone. The audio circuit 560 can transmit the electrical signal converted from the received audio data to the loudspeaker 561, and the loudspeaker 561 converts it into an audio signal output; After being received, it is converted into audio data, and then the audio data is processed by the output processor 580, and then sent to another mobile phone through the RF circuit 510, or the audio data is output to the memory 520 for further processing.

WiFi is a short-distance wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages, and access streaming media through the WiFi module 570, which provides users with wireless broadband Internet access. Although Fig. 5 shows a WiFi module 570, it can be understood that it is not an essential component of the mobile phone, and can be completely omitted as required without changing the essence of the invention.

The processor 580 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and/or modules stored in the memory 520, and calling data stored in the memory 520, execution Various functions and processing data of the mobile phone, so as to monitor the mobile phone as a whole. Optionally, the processor 580 may include one or more processing units; preferably, the processor 580 may integrate an application processor and a modem processor, wherein the application processor mainly processes operating systems, user interfaces, and application programs, etc. , the modem processor mainly handles wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 580 .

The mobile phone also includes a power supply 590 (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the processor 580 through the power management system, so as to realize functions such as managing charging, discharging, and power consumption management through the power management system.

Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be repeated here.

In the embodiment of the present invention, the processor 580 included in the terminal also has the following functions:

Obtain the original image data collected by the camera;

identifying human body image data in the raw image data;

Detecting skin color image data belonging to human body parts in the human body image data;

setting a target skin color value for the human body part according to the characteristic information of the human body image data;

performing normalization processing on the skin color image data according to the target skin color value to obtain target image data.

Optionally, the processor 580 included in the terminal also has the following functions:

Selecting characteristic skin color image data in the skin color image data;

Perform normalization processing on the characteristic skin color image data according to the target skin color value to obtain target image data.

Optionally, the processor 580 included in the terminal also has the following functions:

Count the brightness and/or exposure of the skin color image data;

Select image data whose brightness is within a preset brightness range and/or whose exposure is less than a preset exposure threshold from the skin color image data as characteristic skin color image data.

Optionally, the processor 580 included in the terminal also has the following functions:

Identifying one or more characteristic information in the age information, gender information, and race information of the human body image data;

Query the target skin color value corresponding to the human body part based on one or more characteristic information in age information, gender information, and race information.

Optionally, the processor 580 included in the terminal also has the following functions:

For each skin color image data, count the original skin color value in the part image data;

calculating a normalization coefficient by using the original skin color value and the target skin color value;

On the basis of the original skin color value, adjust with the normalization coefficient to obtain a normalized skin color value;

In the original image data, the skin color image data is adjusted with the normalized skin color value to obtain target image data.

Optionally, the processor 580 included in the terminal also has the following functions:

Obtain the pixel color value of each pixel in the skin color image data;

Calculate the average value of the pixel color values as the original skin color value.

Optionally, the processor 580 included in the terminal also has the following functions:

calculating the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio;

multiplying the pixel color value of each pixel in the part image data by the adjustment ratio to obtain a set of pixel color values;

selecting a target pixel color value from the set of pixel color values;

A normalization coefficient is calculated by using the color adjustment ratio and the target pixel color value.

Optionally, the processor 580 included in the terminal also has the following functions:

From the set of pixel color values, select the pixel color value with the largest value as the target pixel color value.

Optionally, the processor 580 included in the terminal also has the following functions:

calculating the ratio between the preset color threshold and the target pixel color value as the pixel color ratio;

Calculate the product of the color adjustment ratio and the pixel color ratio to obtain a normalization coefficient.

Optionally, the processor 580 included in the terminal also has the following functions:

performing image processing on the original image data;

Wherein, the image processing includes at least one of the following:

Automatic exposure control, white balance adjustment, color restoration processing, color enhancement processing, denoising processing.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: Read Only Memory (ROM, Read Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

Those of ordinary skill in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the above-mentioned storage The medium can be read-only memory, magnetic or optical disk, etc.

The mobile terminal provided by the present invention has been introduced in detail above. For those of ordinary skill in the art, according to the idea of the embodiment of the present invention, there will be changes in the specific implementation and application range. In summary, , the contents of this specification should not be construed as limiting the present invention.

The embodiment of the present invention discloses A1. A method for processing image data, including: acquiring original image data collected by a camera; identifying human body image data in the original image data; detecting human body image data in the human body image data The skin color image data of the part; setting the target skin color value for the human body part according to the characteristic information of the human body image data; performing normalization processing on the skin color image data according to the target skin color value to obtain the target image data. A2. The method as described in A1, wherein the skin color image data is normalized according to the target skin color value, and the step of obtaining the target image data includes: selecting characteristic skin color image data in the skin color image data ; performing normalization processing on the characteristic skin color image data according to the target skin color value to obtain target image data. A3, the method as described in A2, the step of selecting characteristic skin color image data in the skin color image data includes: counting the brightness and/or exposure of the skin color image data; selecting brightness from the skin color image data Image data within a preset brightness range and/or exposure less than a preset exposure threshold is used as characteristic skin color image data. A4. The method as described in A1 or A2 or A3, the step of setting the target skin color value for the human body part according to the characteristic information of the human body image data includes: identifying the age information and gender information of the human body image data 1. One or more characteristic information in the ethnic information; query the target skin color value corresponding to the human body part based on one or more characteristic information in the age information, gender information, and ethnic information. A5, the method as described in A1 or A2 or A3, said skin color image data is normalized according to said target skin color value, and the step of obtaining target image data includes: for each skin color image data, statistics The original skin color value in the part image data; using the original skin color value and the target skin color value to calculate a normalization coefficient; on the basis of the original skin color value with the normalization coefficient adjusting to obtain a normalized skin color value; in the original image data, adjusting the skin color image data with the normalized skin color value to obtain target image data. A6, the method as described in A5, the step of counting the original skin color value in the skin color image data includes: obtaining the pixel color value of each pixel in the skin color image data; calculating the average of the pixel color values value, as the original skin color value. A7. The method as described in A5, the step of calculating the normalization coefficient by using the original skin color value and the target skin color value includes: calculating the difference between the target skin color value and the original skin color value to obtain the color adjustment ratio; multiply the pixel color value of each pixel in the part image data by the adjustment ratio to obtain a pixel color value set; select the target pixel color value from the pixel color value set; The color adjustment ratio and the target pixel color value calculate a normalization coefficient. A8. The method as described in A7, the step of selecting the target pixel color value from the pixel color value set includes: selecting the pixel color value with the largest value from the pixel color value set as the target pixel color value. A9, the method as described in A7, the step of calculating the normalization coefficient by using the color adjustment ratio and the target pixel color value includes: calculating the ratio between the preset color threshold and the target pixel color value , as a pixel color ratio; calculate the product of the color adjustment ratio and the pixel color ratio to obtain a normalization coefficient. A10. The method according to any one of A1-A9, before the step of identifying human body image data from the original image data, the method further includes: performing image processing on the original image data; wherein, The image processing includes at least one of the following: automatic exposure control, white balance adjustment, color restoration processing, color enhancement processing, and noise removal processing.

The implementation of the present invention also discloses B11, an image data processing device, including: an original image data acquisition module, used to acquire the original image data collected by the camera; a human body image data recognition module, used to identify Human body image data; skin color image data detection module, used to detect skin color image data belonging to human body parts in the human body image data; target skin color value setting module, used to target all skin color values according to the characteristic information of the human body image data The target skin color value is set for the human body part; the normalization processing module is used to perform normalization processing on the skin color image data according to the target skin color value to obtain target image data. B12, the device as described in B11, the normalization processing module is also used for: selecting characteristic skin color image data in the skin color image data; normalizing the characteristic skin color image data according to the target skin color value process to obtain the target image data. B13, the device as described in B12, the normalization processing module is also used to: count the brightness and/or exposure of the skin color image data; select the brightness from the skin color image data in the preset brightness interval and /or image data whose exposure is less than a preset exposure threshold is used as characteristic skin color image data. B14, the device as described in B11 or B12 or B13, the target skin color value setting module is also used to: identify one or more characteristic information in the age information, gender information, and race information of the human body image data ; Query the target skin color value corresponding to the human body part based on one or more characteristic information in age information, gender information, and race information. B15, the device as described in B11 or B12 or B13, the normalization processing module is also used for: for each skin color image data, count the original skin color value in the part image data; adopt the original skin color value and the target skin color value to calculate a normalization coefficient; on the basis of the original skin color value, adjust with the normalization coefficient to obtain a normalized skin color value; in the original image data, adjusting the skin color image data with the normalized skin color value to obtain target image data. B16, the device as described in B15, the normalization processing module is also used to: obtain the pixel color value of each pixel in the skin color image data; calculate the average value of the pixel color value as the original skin color value . B17, the device as described in B15, the normalization processing module is also used to: calculate the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio; Multiply the pixel color value of each pixel in the pixel by the adjustment ratio to obtain a pixel color value set; select the target pixel color value from the pixel color value set; use the color adjustment ratio and the target pixel color value to calculate the return Unification coefficient. B18. The device according to B17, wherein the normalization processing module is further configured to: select the pixel color value with the largest value from the set of pixel color values as the target pixel color value. B19, the device as described in B17, the normalization processing module is also used to: calculate the ratio between the preset color threshold and the target pixel color value as the pixel color ratio; calculate the color adjustment ratio and The product between the pixel color scales to obtain the normalization coefficient. B20. The device according to any one of B11-B19, further comprising: an image processing module configured to perform image processing on the raw image data; wherein the image processing includes at least one of the following: automatic exposure control, White balance adjustment, color restoration processing, color enhancement processing, denoising processing.

The embodiment of the present invention also discloses C21, a mobile terminal, including: a memory and a processor; wherein, the memory is used to store instructions for acquiring the original image data collected by the camera, and the human body image is identified in the original image data Instructions for data, an instruction for detecting skin color image data belonging to human body parts in the human body image data, an instruction for setting a target skin color value for the human body part according to the characteristic information of the human body image data, and an instruction for setting a target skin color value according to the target skin color The color value is used to normalize the skin color image data to obtain an instruction for target image data; the processor is used to: obtain the original image data collected by the camera according to the instruction for obtaining the original image data collected by the camera; according to the instruction for obtaining the original image data collected by the camera According to the instruction of identifying human body image data in the original image data, the human body image data is identified in the original image data; according to the instruction of detecting skin color image data belonging to parts of the human body in the human body image data, in Detecting skin color image data belonging to human body parts in the human body image data; according to the instruction of setting a target skin color value for the human body parts according to the characteristic information of the human body image data, according to the characteristic information of the human body image data Set a target skin color value for the human body part; perform normalization processing on the skin color image data according to the target skin color value to obtain the target image data, and set the target skin color value according to the target skin color value. The skin color image data is normalized to obtain the target image data. C22. The mobile terminal as described in C21, the processor is further configured to: select characteristic skin color image data in the skin color image data; perform normalization processing on the characteristic skin color image data according to the target skin color value , to obtain the target image data. C23. The mobile terminal as described in C22, the processor is further configured to: count the brightness and/or exposure of the skin color image data; select the brightness from the skin color image data within a preset brightness range and/or Image data whose exposure is less than a preset exposure threshold is used as characteristic skin color image data. C24. The mobile terminal as described in C21 or C22 or C23, the processor is also used to: identify one or more characteristic information in the age information, gender information, and race information of the human body image data; information, gender information, and race information to query the target skin color value corresponding to the human body part. C25, the mobile terminal as described in C21 or C22 or C23, the processor is also used to: for each skin color image data, count the original skin color value in the part image data; use the original skin color value and Calculate a normalization coefficient for the target skin color value; adjust with the normalization coefficient on the basis of the original skin color value to obtain a normalized skin color value; in the original image data, the The normalized skin color value is used to adjust the skin color image data to obtain target image data. C26. The mobile terminal as described in C25, wherein the processor is further configured to: acquire pixel color values of each pixel in the skin color image data; calculate an average value of the pixel color values as the original skin color value. C27. The mobile terminal as described in C25, the processor is further configured to: calculate the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio; Multiplying the pixel color value of the pixel point by the adjustment ratio to obtain a pixel color value set; selecting a target pixel color value from the pixel color value set; calculating normalization by using the color adjustment ratio and the target pixel color value coefficient. C28. The mobile terminal according to C27, wherein the processor is further configured to: select a pixel color value with the largest value from the set of pixel color values as the target pixel color value. C29. The mobile terminal as described in C27, the processor is further configured to: calculate a ratio between a preset color threshold and the target pixel color value as a pixel color ratio; calculate the color adjustment ratio and the The product between the pixel color scales to obtain the normalization factor. C30. The mobile terminal according to any one of C21-C29, the memory is also used to store instructions for performing image processing on the original image data; the processor is also used to: according to the An instruction for performing image processing on the data, performing image processing on the original image data; wherein, the image processing includes at least one of the following: automatic exposure control, white balance adjustment, color restoration processing, color enhancement processing, and denoising processing.

Claims (10)

1. A method for processing image data, comprising: Obtain the original image data collected by the camera; identifying human body image data in the raw image data; Detecting skin color image data belonging to human body parts in the human body image data; setting a target skin color value for the human body part according to the characteristic information of the human body image data; performing normalization processing on the skin color image data according to the target skin color value to obtain target image data. 2. The method according to claim 1, wherein said skin color image data is normalized according to said target skin color value, and the step of obtaining target image data comprises: Selecting characteristic skin color image data in the skin color image data; Perform normalization processing on the characteristic skin color image data according to the target skin color value to obtain target image data. 3. The method according to claim 2, wherein the step of selecting characteristic skin color image data in the skin color image data comprises: Count the brightness and/or exposure of the skin color image data; Select image data whose brightness is within a preset brightness range and/or whose exposure is less than a preset exposure threshold from the skin color image data as characteristic skin color image data. 4. The method according to claim 1 or 2 or 3, wherein the step of setting the target skin color value for the human body part according to the feature information of the human body image data comprises: Identifying one or more characteristic information in the age information, gender information, and race information of the human body image data; Query the target skin color value corresponding to the human body part based on one or more characteristic information in age information, gender information, and race information. 5. the method as claimed in claim 1 or 2 or 3, is characterized in that, described skin color image data is carried out normalization process according to described target skin color value, the step of obtaining target image data comprises: For each skin color image data, count the original skin color value in the part image data; calculating a normalization coefficient by using the original skin color value and the target skin color value; On the basis of the original skin color value, adjust with the normalization coefficient to obtain a normalized skin color value; In the original image data, the skin color image data is adjusted with the normalized skin color value to obtain target image data. 6. method as claimed in claim 5, is characterized in that, the step of the original skin color value in described statistics described skin color image data comprises: Obtain the pixel color value of each pixel in the skin color image data; Calculate the average value of the pixel color values as the original skin color value. 7. The method according to claim 5, wherein the step of calculating a normalization coefficient using the original skin color value and the target skin color value comprises: calculating the ratio between the target skin color value and the original skin color value to obtain a color adjustment ratio; multiplying the pixel color value of each pixel in the part image data by the adjustment ratio to obtain a set of pixel color values; selecting a target pixel color value from the set of pixel color values; A normalization coefficient is calculated by using the color adjustment ratio and the target pixel color value. 8. The method according to claim 7, wherein the step of selecting a target pixel color value from the set of pixel color values comprises: From the set of pixel color values, select the pixel color value with the largest value as the target pixel color value. 9. A processing device for image data, comprising: The original image data acquisition module is used to obtain the original image data collected by the camera; A human body image data identification module, configured to identify the human body image data in the original image data; A skin color image data detection module, configured to detect skin color image data belonging to human body parts in the human body image data; A target skin color value setting module, configured to set a target skin color value for the human body part according to the characteristic information of the human body image data; A normalization processing module, configured to perform normalization processing on the skin color image data according to the target skin color value to obtain target image data. 10. A mobile terminal, comprising: memory and processor; Wherein, the memory is used to store the instruction for acquiring the original image data collected by the camera, the instruction for identifying the human body image data in the original image data, and the detection of the skin color image data belonging to the human body parts in the human body image data An instruction, an instruction of setting a target skin color value for the human body part according to the characteristic information of the human body image data, performing normalization processing on the skin color image data according to the target skin color value, and obtaining an instruction of the target image data; The processor is used to: Acquire the original image data collected by the camera according to the instruction for obtaining the original image data collected by the camera; identifying human body image data in the original image data according to the instruction for identifying human body image data in the original image data; According to the instruction of detecting skin color image data belonging to human body parts in the human body image data, detecting skin color image data belonging to human body parts in the human body image data; According to the instruction of setting a target skin color value for the human body part according to the characteristic information of the human body image data, set a target skin color value for the human body part according to the characteristic information of the human body image data; According to the instruction of normalizing the skin color image data according to the target skin color value to obtain the target image data, normalizing the skin color image data according to the target skin color value to obtain the target image data.