CN107862658B - Image processing method, apparatus, computer-readable storage medium and electronic device - Google Patents

Abstract

The present application relates to an image processing method, device, computer-readable storage medium and electronic device. The method comprises: obtaining an image to be processed; obtaining the brightness value corresponding to each channel image in the image to be processed, and obtaining the beauty parameters corresponding to each channel image according to the brightness value; performing beauty processing on each channel image according to the beauty parameters; and fusing the channel images after the beauty processing to obtain a beauty image. The above-mentioned image processing method, device, computer-readable storage medium and electronic device improve the accuracy of image processing.

Description

Image processing method, apparatus, computer-readable storage medium and electronic device

technical field

The present application relates to the technical field of image processing, and in particular, to an image processing method, apparatus, computer-readable storage medium, and electronic device.

Background technique

Whether it is at work or in life, taking pictures is an essential skill. In order to take a satisfactory photo, it is not only necessary to improve the shooting parameters during the shooting process, but also to improve the photo itself after the shooting is completed. Beauty processing refers to a method of beautifying photos. After beauty processing, the characters in the photos will look more in line with human aesthetics.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an image processing method, apparatus, computer-readable storage medium, and electronic device, which can improve the accuracy of image processing.

An image processing method, the method comprising:

Get the image to be processed;

Acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value;

Performing beautification processing on the respective channel images according to the beautifying parameters;

The image of each channel after the beauty treatment is fused to obtain a beauty image.

An image processing device, the device comprising:

Image acquisition module, used to acquire the image to be processed;

A parameter acquisition module, configured to acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value;

A beauty processing module, configured to perform beauty processing on the respective channel images according to the beauty parameters;

The image fusion module is used for fusing each channel image after the beauty treatment to obtain a beauty image.

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Get the image to be processed;

Acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value;

Performing beautification processing on the respective channel images according to the beautifying parameters;

The image of each channel after the beauty treatment is fused to obtain a beauty image.

An electronic device, comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the instructions are executed by the processor, the processor is caused to perform the following steps:

Get the image to be processed;

Acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value;

Performing beautification processing on the respective channel images according to the beautifying parameters;

The image of each channel after the beauty treatment is fused to obtain a beauty image.

The above-mentioned image processing method, device, computer-readable storage medium and electronic equipment, first obtain the brightness value of each channel image in the image to be processed, and obtain the beauty parameters of each channel image according to the brightness value, and then according to the obtained beauty parameters. Each channel image is beautified. In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

Fig. 1 is the application environment diagram of the image processing method in one embodiment;

2 is a flowchart of an image processing method in one embodiment;

3 is a flowchart of an image processing method in another embodiment;

4 is a schematic diagram of acquiring depth information in one embodiment;

5 is a flowchart of an image processing method in yet another embodiment;

6 is a flowchart of an image processing method in yet another embodiment;

7 is a schematic structural diagram of an image processing apparatus in an embodiment;

8 is a schematic structural diagram of an image processing system in one embodiment;

FIG. 9 is a schematic diagram of an image processing circuit in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first acquisition module may be referred to as a second acquisition module, and similarly, a second acquisition module may be referred to as a first acquisition module, without departing from the scope of this application. Both the first acquisition module and the second acquisition module are acquisition modules, but they are not the same acquisition module.

FIG. 1 is an application environment diagram of an image processing method in one embodiment. As shown in FIG. 1 , the application environment includes a user terminal 102 and a server 104 . The user terminal 102 can be used to collect the to-be-processed image, generate the to-be-processed image, and then send the to-be-processed image to the server 104 . After receiving the to-be-processed image, the server 104 acquires the brightness value corresponding to each channel image in the to-be-processed image, and acquires the beauty parameter corresponding to each channel image according to the brightness value; and performs beauty processing on each channel image according to the beauty parameter; The image of each channel after beautification processing is fused to obtain a beauty image. Finally, the server 104 returns the beauty image to the user terminal 102 . It can be understood that the user terminal 102 can send an image set to the server 104, and the image set includes multiple images. After receiving the image set, the server 104 performs beautification processing on the images in the image set. The user terminal 102 is an electronic device located at the outermost periphery of the computer network and is mainly used for inputting user information and outputting processing results, such as a personal computer, mobile terminal, personal digital assistant, wearable electronic device and the like. The server 104 is a device used to respond to service requests while providing computing services, and may be, for example, one or more computers. It can be understood that, in other embodiments provided in this application, the application environment of the image processing method may only include the user terminal 102, that is, the user terminal 102 is used to collect the image to be processed and perform beauty processing on the image to be processed. .

FIG. 2 is a flowchart of an image processing method in one embodiment. As shown in FIG. 2 , the image processing method includes steps 202 to 206 . in:

Step 202, acquiring an image to be processed.

In one embodiment, the image to be processed refers to an image that needs to be processed for beauty. The image to be processed may be collected by a mobile terminal. A camera that can be used for shooting is installed on the mobile terminal, the user can initiate a photographing instruction through the mobile terminal, and after detecting the photographing instruction, the mobile terminal collects and photographed images through the camera. The mobile terminal will store the collected images to form an image set. It can be understood that, the image to be processed may also be obtained through other means, which is not limited here. For example, the image to be processed may also be downloaded from a web page, or imported from an external storage device, and so on. Acquiring the image to be processed may specifically include: receiving a beauty instruction input by the user, and acquiring the image to be processed according to the beauty instruction, wherein the beauty instruction includes an image identifier. The image identifier refers to a unique identifier that distinguishes different images to be processed, and the image to be processed is obtained according to the image identifier. For example, the image identification may be one or more of image name, image code, image storage address, and the like. Specifically, after acquiring the to-be-processed image, the mobile terminal may perform beauty processing locally on the mobile terminal, or may send the to-be-processed image to the server for beauty processing.

Step 204: Obtain the brightness value corresponding to each channel image in the image to be processed, and obtain the beauty parameter corresponding to each channel image according to the brightness value.

Specifically, the image to be processed is composed of several pixel points, each pixel point may be composed of multiple color channels, and each color channel represents a color component. For example, an image may be composed of three channels of RGB (Red Green Blue, red, green, and blue), or may be composed of three channels of CMY (Cyan Magenta Yellow, magenta, cyan, and yellow). In the process of image processing, each color component of the image can be extracted by a function, and each color component can be processed separately. For example, in Matlab, the image named "rainbow.jpg" is read through the imread() function, and im=imread('rainbow.jpg'), then the RGB color components can be passed through the function r=im(:,:,1) , g=im(:,:,2), b=im(:,:,3) to extract. The channel image is the image formed by the pixels of each color channel in the image to be processed. When the image is beautified, each color channel of the image can be beautified separately, and the processing of each color channel can be different.

Brightness refers to the brightness of the image, and the brightness value can reflect the degree of deviation of the image. The method for obtaining the beauty degree parameter according to the brightness value may specifically include: obtaining the brightness reference value corresponding to each channel image, and obtaining the beauty parameter of each channel image according to the difference between the obtained brightness value and the brightness reference value. For example, a standard RGB channel value of the skin color may be established first, assuming that the RGB channel values corresponding to the standard skin color are 233, 206, and 188, respectively. When whitening the skin area, the brightness values of the three RGB channels can be obtained separately, and the brightness values can be compared with the standard channel values. The larger the color parameter. Specifically, the brightness values in each channel image may be acquired respectively, and the beauty parameters corresponding to each channel image may be acquired according to the acquired brightness values. Beauty parameters refer to parameters for beautifying an image, which can reflect the degree of beautifying an image. For example, when microdermabrasion is performed on an image, the corresponding beauty parameter can be the beauty level, which can be divided into level 1, level 2, and level 3, and the degree of microdermabrasion is gradually increased from level 1 to level 3 .

Step 206: Perform beautification processing on each channel image according to the beauty parameters.

Beauty processing refers to a method of beautifying an image, specifically a method of beautifying a portrait in an image. In general, beauty processing can be performed on the entire image, or only on a region in the image. For example, the beauty treatment can include whitening, skin resurfacing, face-lifting, and weight-loss processing. Whitening and skin resurfacing can improve the brightness and smoothness of the image. Then whitening and skin resurfacing can be performed on the entire image. , slimming and other processing can only be processed for the area where the portrait is located. The brightness value of the image to be processed has a corresponding relationship with the beauty parameter, the beauty parameter of each channel image is obtained according to the brightness value, and the beauty treatment is performed on each channel image according to the beauty parameter. It can be understood that the corresponding relationship between the brightness value and the beauty parameter may be a linear functional relationship or a nonlinear functional relationship. For example, in an RGB image, the image may include an R channel image, a G channel image, and a B channel image. The brightness values corresponding to these three channel images are 50, 210, and 130, respectively, and the corresponding beauty levels are 1 and 3, respectively. Level 1, Level 2, you need to perform Level 1, Level 3, Level 2 beautification processing on the R channel image, G channel image, and B channel image, respectively.

Step 208 , fuse each channel image after beautification processing to obtain a beautification image.

In one embodiment, image fusion refers to a process of synthesizing multiple images to generate a target image. After each channel image of the to-be-processed image is subjected to beautification processing, each channel image after the beautification processing is fused to obtain a final beautified image. The beautification process is performed according to the brightness value in each channel image. The channel image with the lower brightness value indicates that the brightness deviation is more serious. Obtain the corresponding beauty parameters according to the brightness deviation, and perform beauty processing on each channel image respectively. For example, during the skin resurfacing process, the brightness value of the G channel image is the highest. In order to retain the detail information of the brightness area of the G channel image, the G channel image can be subjected to a shallow resurfacing process.

The image processing method, device, computer-readable storage medium and electronic device provided by the above-mentioned embodiments first obtain the brightness value of each channel image in the image to be processed, and obtain the beauty parameters of each channel image according to the brightness value, and then according to the obtained value. The beautification parameters perform beautification processing on each channel image. In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

FIG. 3 is a flowchart of an image processing method in another embodiment. As shown in FIG. 3 , the image processing method includes steps 302 to 310 . in:

Step 302, acquiring the image to be processed.

In one embodiment, the image to be processed may be acquired through a mobile terminal, and after the image to be processed is acquired, beautification processing may be performed locally on the mobile terminal, or may be sent to a server for beautification processing. If the beautification process is performed on the server, an image to be processed may be sent to the server, and the set of images to be processed refers to a set composed of one or more images to be processed. Each mobile terminal may send the set of images to be processed to the server, and after receiving the set of images to be processed, the server performs beauty processing on the images to be processed in the set of images to be processed. When the mobile terminal sends the set of images to be processed, it also sends the corresponding terminal identifier. After the server finishes processing, it searches for the corresponding mobile terminal according to the terminal identifier, and sends the set of images to be processed after the processing is completed to the mobile terminal. The terminal identifier refers to the unique identifier of the user terminal. For example, the terminal identifier may be at least one of an IP (Internet Protocol, protocol for interconnection between networks) address, a MAC (Media Access Control, media access control) address, and the like.

Step 304, acquiring the target area in the image to be processed.

In general, what the user pays attention to is not the whole area in the image, but a certain area in the image. For example, the user generally pays more attention to the area where the portrait is located in the image, or the area where the human face is located. The target area refers to the area that the user pays more attention to. When obtaining the beauty parameters, it is not necessary to obtain the brightness value of the entire image, but only the brightness value of the target area. For example, the target area may refer to a face area, a portrait area, a skin area, a lip area, etc., which is not limited herein. Specifically, the target area may refer to a face area or a portrait area in the image to be processed, wherein the face area refers to the area where the face of the portrait in the image to be processed is located, and the portrait area refers to the location of the entire portrait in the image to be processed. Area. Acquiring the target area in the image to be processed may specifically include: detecting the face area in the image to be processed, and using the face area as the target area; and/or detecting the face area in the image to be processed, and obtaining the portrait according to the face area area, take the portrait area as the target area.

It is not difficult to understand that the image to be processed is composed of several pixels, and the face area is an area composed of pixels corresponding to the face in the image to be processed. Specifically, the face region of the image to be processed can be obtained through a face detection algorithm. The face detection algorithm can include a detection method based on geometric features, an eigenface detection method, a linear discriminant analysis method, a detection method based on a hidden Markov model, etc. This is not limited. Generally, when an image is acquired by an image acquisition device, a depth map corresponding to the image can be acquired at the same time, and the pixels in the depth map correspond to the pixels in the image. The pixels in the depth map represent the depth information of the corresponding pixels in the image, and the depth information is the depth information from the object corresponding to the pixel to the image acquisition device. For example, the depth information can be acquired through dual cameras, and the depth information corresponding to the obtained pixels can be 1 meter, 2 meters, or 3 meters, etc. The obtaining of the portrait region may specifically include: obtaining the image to be processed and corresponding depth information; detecting the face region in the image to be processed, and obtaining the portrait region in the image to be processed according to the face region and the depth information. It is generally considered that the portrait and the face are on the same vertical plane, and the depth information from the portrait to the image acquisition device and the depth information from the human face to the image acquisition device are in the same range. Therefore, after obtaining the face region, the depth information corresponding to the face region can be obtained from the depth map, and then the depth information corresponding to the portrait region can be obtained according to the depth information corresponding to the face region, and then according to the depth information corresponding to the portrait region, namely The portrait area in the image to be processed can be obtained.

FIG. 4 is a schematic diagram of acquiring depth information in one embodiment. As shown in FIG. 4 , the distance T _c between the first camera 402 and the second camera 404 is known, and images corresponding to the object 406 are captured by the first camera 402 and the second camera 404 respectively, and the first clip can be obtained according to the images. _The angle A1 and the second included angle A2, the vertical intersection between the horizontal line where the first camera 402 to the second camera 404 are located and the object 402 is the intersection 408 . Assuming that the distance from the first camera 402 to the intersection 408 is T _x , the distance from the intersection 408 to the second camera 404 is T _c −T _x , and the depth information of the object 406 , that is, the vertical distance from the object 406 to the intersection 408 is T _s . According to the triangle formed by the first camera 402, the object 406 and the intersection 408, the following formula can be obtained:

Similarly, according to the triangle formed by the second camera 404, the object 406 and the intersection 408, the following formula can be obtained:

From the above formula, the depth information of the object 406 can be obtained as:

Step 306: Obtain the brightness value corresponding to each channel image of the target area, and obtain the beauty parameter corresponding to each channel image according to the brightness value.

Obtain the brightness value corresponding to each channel image of the target area, and obtain the beauty parameter corresponding to each channel image according to the brightness value. For example, the brightness value of the CMY channel image corresponding to the face region in the image to be processed is obtained. If the brightness value corresponding to the C channel image is the largest, the C channel image corresponding to the to-be-processed image has the lowest degree of skin grinding. It can be understood that, when performing beauty processing, it is not necessary to process the entire image to be processed, but only the target area. The beauty parameters corresponding to each channel image of the target area can be obtained according to the brightness value and According to the beautification parameters, beautification processing is performed on each channel image of the target area respectively. Generally speaking, the image to be processed may contain one or more target areas, each target area may be an independent connected area, and these independent target areas are extracted from the image to be processed. When obtaining the brightness value of the target area, if there are two or more target areas in the image to be processed, the multiple target areas can be taken as a whole to obtain the brightness values corresponding to each channel image, and according to the obtained brightness values The brightness value is used to obtain the beauty parameters of each channel image, and the brightness value of each channel image corresponding to each target area can also be obtained separately, and the beauty parameters of each channel image corresponding to each target area can be obtained according to the brightness value. For example, if the image to be processed includes face 1 and face 2, when acquiring the beauty parameters, the luminance value of the RGB three-channel image can be obtained by taking the face 1 and face 2 as a whole, and obtaining the luminance value Beauty parameters of the RGB three-channel image corresponding to the image to be processed. The brightness values of the face 1 and the face 2 can also be obtained respectively, and the beauty parameters corresponding to the face 1 and the face 2 can be obtained respectively according to the obtained brightness values. Specifically, the brightness value of the RGB three-channel image corresponding to face 1 is obtained, and the beauty parameters of the RGB three-channel image corresponding to face 1 are respectively obtained according to the obtained brightness value; the brightness of the RGB three-channel image corresponding to face 2 is obtained. value, and obtain the beauty parameters of the RGB three-channel image corresponding to face 2 according to the obtained brightness value.

Specifically, when the face area is beautified, the area of the face area in the image may be different. Generally, the area of the main face that needs to be prominent is relatively large, and the area of the face of passers-by is relatively small. At the same time, when the face area is relatively small, if processing such as microdermabrasion is performed, the facial features of the face will become blurred after processing. When performing beauty processing, the area corresponding to the target area can be obtained. If the area area is smaller than the area threshold, the beauty processing is not performed, and only the target area whose area is larger than the area threshold is subjected to the beauty processing. Then, before step 306, the method may further include: acquiring the area of the target area, and acquiring the face area whose area is greater than the area threshold. The target area is composed of several pixels, and the area of the target area can be expressed as the total number of pixels contained in the target area, or as the area ratio of the target area to the corresponding image to be processed.

Step 308: Perform beautification processing on each channel image according to the beauty parameters.

In one embodiment, the beauty parameters of each channel image in the image to be processed are obtained according to the brightness value of the target area, and the beauty treatment is performed on each channel image in the image to be processed according to the obtained beauty parameters. It is also possible to process only the target area, that is, obtain the brightness value of the target area, obtain the beauty parameters corresponding to each channel image of the target area according to the brightness value, and perform the processing on each channel image of the target area according to the obtained beauty parameters. Beauty treatment. For example, the brightness value of the RGB three-channel image corresponding to the skin area can be obtained, and the RGB three-channel image whitening level of the skin area can be obtained according to the obtained brightness value, and then the RGB three-channel image of the skin area can be processed according to the obtained whitening level. Corresponding degree of whitening treatment.

Step 310 , fuse each channel image after beautification processing to obtain a beautification image.

In one embodiment, if only the target area in the to-be-processed image is subjected to beautification processing, and the remaining areas of the to-be-processed image other than the target area are not subjected to cosmetic beautification processing, the target area and the remaining area may be affected after processing. There are clear differences between them. For example, after whitening the target area, the target area is significantly brighter than the remaining area, which makes the image look unnatural. Then, in the generated beauty image, the boundary of the target area can be transitioned, so that the obtained beauty image looks more natural.

In the image processing method provided by the above embodiment, the brightness value of each channel image of the target area in the image to be processed is first obtained, and the beauty parameters of each channel image are obtained according to the brightness value, and then each channel image is processed according to the obtained beauty parameters. Beauty treatment. In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

FIG. 5 is a flowchart of an image processing method in yet another embodiment. As shown in FIG. 5 , the image processing method includes steps 502 to 512 . in:

Step 502, acquiring the image to be processed.

Step 504: Obtain the brightness value corresponding to each channel image in the image to be processed.

It can be understood that the image to be processed is composed of several pixel points, and these pixel points are arranged according to a certain rule. Generally speaking, the image to be processed is a two-dimensional pixel array, each pixel has a corresponding channel value, and the position of the pixel in the image can be represented by a position coordinate. For example, the image to be processed can be 640*480, which means that the image to be processed has 640 pixels in each length direction and 480 pixels in each width direction, and the total number of pixels is 640*480 =307200, that is, the image to be processed is 300,000 pixels. To obtain the brightness value corresponding to each channel image in the to-be-processed image, each channel image of the to-be-processed image can be obtained first, then each pixel in the channel image is traversed, and the brightness value is obtained according to the obtained channel value of each pixel. For example, the G channel image of the image to be processed is obtained, each pixel in the G channel image is traversed, the G channel value is obtained, and the average value of the G channel values of all pixels is used as the brightness value of the G channel image. It can be understood that, if only the brightness values of each channel image of a certain area are counted, then only the pixels of the area need to be traversed, and the brightness value of the corresponding channel image can be obtained.

Step 506: Acquire corresponding person attribute features according to the image to be processed.

The character attribute feature refers to a feature representing the character attribute of the character in the image, for example, the character attribute feature may refer to one or more of a gender feature, an age feature, an ethnic feature, and the like. The face area in the image to be processed may be acquired first, and then the corresponding character attributes can be identified according to the face area. Specifically, a face region in the image to be processed is acquired, and a character attribute feature corresponding to the face region is acquired through a feature recognition model. Among them, the feature recognition model refers to a model that recognizes the attributes of a person, and the feature recognition model is obtained by training a set of face samples. The face sample set refers to an image set composed of several face images. The feature recognition model is obtained by training according to the face sample set. Generally, the more face images in the face sample set, the more accurate the feature recognition model obtained by training. . For example, in supervised learning, each face image in the face sample set is marked with a corresponding label to mark the type of face image, and a feature recognition model can be obtained by training the face sample set. The feature recognition model can classify the face area and obtain the corresponding character attribute features. For example, the face area can be divided into yellow, black and white, then the corresponding character attribute feature obtained is one of yellow, black or white. That is, classification by feature recognition models is based on the same criteria. It can be understood that, to obtain character attribute features of different dimensions of the face region, they can be obtained separately through different feature recognition models. Specifically, the character attribute features may include race feature parameters, gender feature parameters, age feature parameters, skin color feature parameters, skin texture feature parameters, face shape feature parameters, and makeup feature parameters, which are not limited herein. For example, the ethnic characteristic parameter corresponding to the face region is obtained through the ethnic identification model, the age characteristic parameter corresponding to the face region is obtained according to the age identification model, and the gender characteristic parameter corresponding to the face region is obtained according to the gender identification model.

Step 508: Obtain the beauty parameters corresponding to the images of each channel according to the character attributes and brightness values.

In one embodiment, the beauty parameter may include a beauty category parameter and a beauty level parameter. Among them, the beauty category parameter is a parameter representing the beauty processing category, and the beauty level parameter is a parameter representing the beauty processing level. For example, the beauty category parameter may be whitening treatment, skin resurfacing treatment, etc., and the beauty level parameter may be divided into five levels, namely, level 1, level 2, level 3, level 4, and level 5. From level 1 to level 5 beautifying treatment, the degree of beautifying treatment increases. After acquiring the human attribute features and brightness values of the image to be processed, the beauty parameters corresponding to each channel image can be acquired according to the human attribute features and brightness values. The character attribute feature corresponds to the beauty category parameter, and the corresponding beauty category parameter can be obtained according to the character attribute feature. The brightness value corresponds to the beauty level parameter, and the corresponding beauty level parameter can be obtained according to the brightness value. For example, when the face in the image is identified as male, the image is subjected to microdermabrasion processing, and when the face in the identified image is identified as female, the image is subjected to whitening processing. Specifically, the beauty category parameter corresponding to the image to be processed is obtained according to the character attribute feature; the beauty level parameter corresponding to each channel image is obtained according to the brightness value. It can be understood that there may be multiple faces in the image to be processed. When there are multiple face regions in the image to be processed, each face region can be identified separately, and the character attributes and brightness corresponding to each face region can be obtained separately. value, and then perform beautification processing for each face area separately.

Step 510: Perform beautification processing on each channel image according to the beauty parameters.

The beauty parameters include a beauty category parameter and a beauty degree parameter, and each channel image is subjected to beautification processing according to the beauty category parameter and the beauty level parameter. Generally speaking, the beauty category parameters corresponding to each channel image are the same, and the corresponding beauty level parameters can be different. For example, if you want to perform microdermabrasion processing on an image, you should perform microdermabrasion processing on each channel image, and the degree of microdermabrasion corresponding to each channel image can be different.

Step 512 , fuse each channel image after beautifying processing to obtain a beautifying image.

In the image processing method provided by the above embodiment, the brightness value of each channel image in the image to be processed is first obtained, and the beauty parameters of each channel image are obtained according to the brightness value, and then the beauty treatment is performed on each channel image according to the obtained beauty parameters. . In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

FIG. 6 is a flowchart of an image processing method in yet another embodiment. As shown in FIG. 6 , the image processing method includes steps 602 to 614 . in:

Step 602, acquiring the image to be processed.

Step 604: Detect the face region in the image to be processed, and obtain brightness values corresponding to each channel image of the face region.

Step 606 , obtaining the character attribute features corresponding to the face region through a feature recognition model, wherein the feature recognition model is obtained by training a set of face samples.

Step 608: Acquire a beauty category parameter corresponding to the image to be processed according to the character attribute feature, where the beauty category parameter is a parameter representing a beauty processing category.

Step 610: Obtain a beauty level parameter corresponding to each channel image according to the brightness value, where the beauty level parameter is a parameter representing the level of beauty processing.

Step 612: Perform beautification processing on each channel image according to the beautification category parameter and the beautification degree parameter.

Step 614 , fuse each channel image after beautification processing to obtain a beautification image.

In the image processing method provided by the above-mentioned embodiments, the face region in the image to be processed is firstly obtained, and the brightness value of each channel image corresponding to the face region is obtained, and the beauty parameters of each channel image are obtained according to the brightness value, and then according to the obtained value. The beautification parameters perform beautification processing on each channel image. In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

FIG. 7 is a schematic structural diagram of an image processing apparatus in an embodiment. As shown in FIG. 7 , the image processing apparatus 700 includes an image acquisition module 702 , a parameter acquisition module 704 , a beauty processing module 706 and an image fusion module 708 . in:

The image acquisition module 702 is used to acquire the image to be processed.

The parameter acquisition module 704 is configured to acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value.

The beauty processing module 706 is configured to perform beauty processing on the respective channel images according to the beauty parameters.

The image fusion module 708 is configured to fuse the images of each channel after the beauty treatment to obtain a beauty image.

The image processing device provided by the above embodiment first obtains the brightness value of each channel image in the image to be processed, and obtains the beauty parameter of each channel image according to the brightness value, and then performs beauty processing on each channel image according to the obtained beauty parameter. . In this way, different beautification processing can be performed for each channel image, which optimizes the beauty processing and makes the image processing more accurate.

In one embodiment, the parameter obtaining module 704 is further configured to obtain the target area in the to-be-processed image; obtain the brightness value corresponding to each channel image of the target area, and obtain the corresponding brightness value of each channel image according to the brightness value Beauty parameters.

In one embodiment, the parameter acquisition module 704 is further configured to detect the face area in the image to be processed, and use the face area as the target area; and/or detect the face area in the image to be processed, and obtain a portrait area according to the face area, and use the portrait area as a target area.

In one embodiment, the parameter obtaining module 704 is further configured to obtain the corresponding human attribute feature according to the to-be-processed image; and obtain the beauty parameter corresponding to each channel image according to the human attribute feature and the brightness value.

In one embodiment, the parameter obtaining module 704 is further configured to obtain the face region in the image to be processed, and obtain the character attribute feature corresponding to the face region through a feature recognition model, wherein the feature recognition model The face sample set is obtained by training.

In one embodiment, the parameter obtaining module 704 is further configured to obtain the beauty category parameter corresponding to the image to be processed according to the character attribute feature, where the beauty category parameter is a parameter representing the beauty treatment category; according to the The brightness value obtains a beauty level parameter corresponding to each channel image, and the beauty level parameter is a parameter representing the level of beauty processing.

In one embodiment, the beauty processing module 706 is further configured to perform beauty processing on the respective channel images according to the beauty category parameter and the beauty level parameter.

The division of each module in the above image processing apparatus is only for illustration. In other embodiments, the image processing apparatus may be divided into different modules as required to complete all or part of the functions of the above image processing apparatus.

FIG. 8 is a schematic structural diagram of an image processing system in one embodiment. As shown in FIG. 8 , the image processing image includes a feature layer 802 , an adaptation layer 804 and a processing layer 806 . Among them, the feature layer 802 is used to acquire the image to be processed, and acquire the brightness value in the image to be processed. Then, face detection is performed on the image to be processed, and corresponding character attribute features are obtained according to the face region obtained by the face detection. The character attribute features may include race feature parameters, gender feature parameters, age feature parameters, skin color feature parameters, skin texture feature parameters, face shape feature parameters, and makeup feature parameters, which are not limited herein. The feature layer 802 sends the acquired brightness value and human attribute features to the adaptation layer 804, and the adaptation layer 804 obtains the corresponding beauty parameters according to the brightness values and human attribute features corresponding to the image to be processed, and sends the beauty parameters to in processing layer 806. The processing layer 806 performs beautification processing on the image to be processed according to the received beauty parameters, and then outputs the image after beautification processing. Among them, the beauty treatment may include, but is not limited to, treatments such as skin resurfacing, whitening, big eyes, face reduction, skin tone adjustment, freckle removal, eye brightening, eye bag removal, teeth whitening, and lip beautification.

Embodiments of the present application also provide a computer-readable storage medium. One or more non-transitory computer-readable storage media containing a computer program that, when executed by one or more processors, causes the processors to perform the following steps:

Get the image to be processed;

Acquire the brightness value corresponding to each channel image in the to-be-processed image, and acquire the beauty parameter corresponding to each channel image according to the brightness value;

Performing beautification processing on the respective channel images according to the beautifying parameters;

The image of each channel after the beauty treatment is fused to obtain a beauty image.

In one embodiment, the acquiring the brightness value corresponding to each channel image in the to-be-processed image performed by the processor, and acquiring the beauty parameter corresponding to each channel image according to the brightness value includes:

obtaining the target area in the to-be-processed image;

The brightness value corresponding to each channel image of the target area is acquired, and the beauty parameter corresponding to each channel image is acquired according to the brightness value.

In one embodiment, the acquiring the target area in the to-be-processed image performed by the processor includes at least one of the following methods:

Detecting the face area in the to-be-processed image, and using the face area as a target area;

A face area in the to-be-processed image is detected, a portrait area is acquired according to the face area, and the portrait area is used as a target area.

In one embodiment, the method performed by the processor further includes:

Obtaining the corresponding character attribute feature according to the to-be-processed image;

The acquiring the beauty parameters corresponding to each channel image according to the brightness value includes:

According to the character attribute feature and the brightness value, the beauty parameters corresponding to the respective channel images are acquired.

In one embodiment, the acquiring the corresponding person attribute feature according to the to-be-processed image performed by the processor includes:

The face region in the image to be processed is acquired, and the character attribute feature corresponding to the face region is acquired through a feature recognition model, wherein the feature recognition model is obtained by training a set of face samples.

In one embodiment, the acquiring, according to the character attribute feature and the brightness value, performed by the processor to obtain the beauty parameters corresponding to the respective channel images includes:

Obtaining a beauty category parameter corresponding to the to-be-processed image according to the character attribute feature, where the beauty category parameter is a parameter representing a beauty treatment category;

The beauty level parameter corresponding to each channel image is acquired according to the brightness value, and the beauty level parameter is a parameter representing the level of beauty processing.

In one embodiment, the performing the beautifying processing on the respective channel images according to the beautifying parameters performed by the processor includes:

According to the beauty category parameter and the beauty level parameter, beautification processing is performed on the respective channel images.

The embodiments of the present application also provide an electronic device. The above electronic device includes an image processing circuit, and the image processing circuit may be implemented by hardware and/or software components, and may include various processing units that define an ISP (Image Signal Processing, image signal processing) pipeline. FIG. 9 is a schematic diagram of an image processing circuit in one embodiment. As shown in FIG. 9 , for the convenience of description, only various aspects of the image processing technology related to the embodiments of the present application are shown.

As shown in FIG. 9 , the image processing circuit includes an ISP processor 940 and a control logic 950 . Image data captured by imaging device 910 is first processed by ISP processor 940 , which analyzes the image data to capture image statistics that can be used to determine and/or control one or more parameters of imaging device 910 . Imaging device 910 may include a camera having one or more lenses 912 and an image sensor 914 . Image sensor 914 may include an array of color filters (eg, Bayer filters), image sensor 914 may obtain light intensity and wavelength information captured with each imaging pixel of image sensor 914 and provide a set of raw materials that may be processed by ISP processor 940. image data. The sensor 920 (eg, a gyroscope) may provide the acquired image processing parameters (eg, anti-shake parameters) to the ISP processor 940 based on the sensor 920 interface type. The sensor 920 interface may utilize a SMIA (Standard Mobile Imaging Architecture) interface, other serial or parallel camera interfaces, or a combination of the above interfaces.

Additionally, image sensor 914 may also send raw image data to sensor 920, which may provide raw image data to ISP processor 940 based on sensor 920 interface type, or sensor 920 may store raw image data in image memory 930.

The ISP processor 940 processes raw image data pixel by pixel in various formats. For example, each image pixel may have a bit depth of 8, 10, 12, or 14 bits, and the ISP processor 940 may perform one or more image processing operations on the raw image data, collecting statistical information about the image data. Among them, the image processing operations can be performed with the same or different bit depth precision.

ISP processor 940 may also receive image data from image memory 930 . For example, the sensor 920 interface sends the raw image data to the image memory 930, and the raw image data in the image memory 930 is provided to the ISP processor 940 for processing. The image memory 930 may be a part of a memory device, a storage device, or an independent dedicated memory within an electronic device, and may include a DMA (Direct Memory Access, direct memory access) feature.

When receiving raw image data from the image sensor 914 interface or from the sensor 920 interface or from the image memory 930, the ISP processor 940 may perform one or more image processing operations, such as temporal filtering. The processed image data may be sent to image memory 930 for additional processing before being displayed. The ISP processor 940 may also receive processed data from the image memory 930 on which to perform image data processing in the original domain and in the RGB and YCbCr color spaces. The processed image data may be output to the display 980 for viewing by a user and/or further processed by a graphics engine or a GPU (Graphics Processing Unit, graphics processor). In addition, the output of the ISP processor 940 may also be sent to the image memory 930 , and the display 980 may read image data from the image memory 930 . In one embodiment, image memory 930 may be configured to implement one or more frame buffers. Additionally, the output of ISP processor 940 may be sent to encoder/decoder 970 for encoding/decoding image data. The encoded image data can be saved and decompressed prior to display on the display 980 device.

The step of processing the image data by the ISP processor 940 includes: performing VFE (Video Front End, video front-end) processing and CPP (Camera Post Processing, camera post-processing) processing on the image data. VFE processing of image data may include correction of contrast or brightness values of image data, modification of digitally recorded lighting state data, compensation processing of image data (such as white balance, automatic gain control, gamma correction, etc.), image data filter processing, etc. CPP processing of image data may include scaling the image, providing preview frames and recording frames to each path. Among them, CPP can use different codecs to process preview frames and record frames. The image data processed by the ISP processor 940 may be sent to the beauty module 960 to perform beauty processing on the image before being displayed. The beauty processing of the image data by the beauty module 960 may include: whitening, freckle removal, skin resurfacing, face reduction, acne removal, eye enlargement, and the like. The beauty module 960 may be a CPU (Central Processing Unit, central processing unit), a GPU, a co-processor, or the like in the mobile terminal. The data processed by the beauty module 960 may be sent to the encoder/decoder 970 for encoding/decoding the image data. The encoded image data can be saved and decompressed prior to display on the display 980 device. The beauty module 960 may also be located between the encoder/decoder 970 and the display 980, that is, the beauty module performs beauty processing on the imaged image. The aforementioned encoder/decoder 970 may be a CPU, a GPU, or a co-processor in the mobile terminal, or the like.

Statistics determined by the ISP processor 940 may be sent to the control logic 950 unit. For example, the statistics may include image sensor 914 statistics such as auto exposure, auto white balance, auto focus, flicker detection, black level compensation, lens 912 shading correction, and the like. Control logic 950 may include a processor and/or microcontroller executing one or more routines (eg, firmware) that may determine control parameters of imaging device 910 and ISP processing based on received statistics control parameters of the controller 940. For example, imaging device 910 control parameters may include sensor 920 control parameters (eg, gain, integration time for exposure control), camera flash control parameters, lens 912 control parameters (eg, focal length for focus or zoom), or a combination of these parameters. ISP control parameters may include gain levels and color correction matrices for automatic white balance and color adjustment (eg, during RGB processing), and lens 912 shading correction parameters.

The image processing method provided by the above embodiment can be implemented by using the image processing technology in FIG. 9 .

A computer program product containing instructions, when run on a computer, causes the computer to execute the image processing method provided by the above embodiments.

Any reference to a memory, storage, database, or other medium as used herein may include non-volatile and/or volatile memory. Suitable nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent of the present application. It should be noted that, for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. an image processing method, is characterized in that, described method comprises: Receive the beauty instruction input by the user to obtain the image to be processed; Obtain each channel image of the image to be processed, traverse each pixel point in the each channel image, take the average value of the channel values of all pixel points in the each channel image as the brightness value corresponding to the each channel image, and according to The difference between the brightness value corresponding to each channel image and the brightness reference value of each channel image is obtained, and the beauty parameter corresponding to each channel image is obtained; wherein, different difference values correspond to different beauty parameters; Performing beautification processing on the respective channel images according to the beautifying parameters; The image of each channel after the beauty treatment is fused to obtain a beauty image. 2 . The image processing method according to claim 1 , wherein the acquiring each channel image of the to-be-processed image, traverses each pixel in the each channel image, and converts the The average value of the channel values of all pixel points is taken as the brightness value corresponding to each channel image, and the beauty parameters corresponding to each channel image are obtained according to the difference between each of the brightness values and the brightness reference value, including: obtaining the target area in the to-be-processed image; Traverse each pixel point in each channel image of the target area, take the average value of all pixel point channel values in each channel image of the target area as the brightness value corresponding to each channel image of the target area, and according to The difference between each of the luminance values and the luminance reference value obtains the beauty parameters corresponding to each channel image. 3. The image processing method according to claim 2, wherein the acquiring the target area in the to-be-processed image comprises at least one of the following methods: Detecting the face area in the to-be-processed image, and using the face area as a target area; A face area in the to-be-processed image is detected, a portrait area is acquired according to the face area, and the portrait area is used as a target area. 4. The image processing method according to any one of claims 1 to 3, wherein the method further comprises: Obtaining the corresponding character attribute feature according to the to-be-processed image; The obtaining the beauty parameters corresponding to each channel image according to the difference between each of the luminance values and the luminance reference value includes: The beauty parameters corresponding to each channel image are acquired according to the character attribute feature and the difference between each of the luminance values and the luminance reference value. 5 . The image processing method according to claim 4 , wherein the obtaining the corresponding character attributes according to the to-be-processed image comprises: 5 . The face region in the image to be processed is acquired, and the character attribute feature corresponding to the face region is acquired through a feature recognition model, wherein the feature recognition model is obtained by training a set of face samples. 6 . The image processing method according to claim 4 , wherein the image processing method corresponding to each channel image is obtained according to the character attribute feature and the difference between each of the luminance values and the luminance reference value. 7 . Color parameters include: Obtaining a beauty category parameter corresponding to the to-be-processed image according to the character attribute feature, where the beauty category parameter is a parameter representing a beauty treatment category; The beauty level parameter corresponding to each channel image is acquired according to the difference between each of the brightness values and the brightness reference value, where the beauty level parameter is a parameter representing the level of beauty processing. 7. The image processing method according to claim 6, wherein the performing beautifying processing on the respective channel images according to the beautifying parameters comprises: According to the beauty category parameter and the beauty level parameter, beautification processing is performed on the respective channel images. 8. An image processing device, wherein the device comprises: an image acquisition module, configured to receive a beautifying instruction input by a user to acquire an image to be processed; the beautifying instruction includes an image identifier; The parameter acquisition module is used to acquire each channel image of the image to be processed, traverse each pixel point in the each channel image, and take the average value of the channel values of all pixel points in the each channel image as the corresponding channel image and according to the difference between the corresponding brightness value of each channel image and the brightness reference value of each channel image, the beauty parameters corresponding to each channel image are obtained; wherein, different difference values correspond to different beauty parameters; A beauty processing module, configured to perform beauty processing on the respective channel images according to the beauty parameters; The image fusion module is used for fusing each channel image after the beauty treatment to obtain a beauty image. 9 . A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the image processing method according to any one of claims 1 to 7 is implemented. 10. An electronic device comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the instructions are executed by the processor, the processor is made to execute any one of claims 1 to 7 The image processing method described in item.

Images