CN107277356B - Method and device for processing human face area of backlight scene - Google Patents

Abstract

The invention discloses a method and a device for processing a face region of a backlight scene, wherein the method comprises the following steps: when a backlight scene is detected, separating a foreground and a backlight background from a current shooting picture; carrying out brightness improvement processing on the foreground, and determining a face area in the foreground; and adjusting the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face region. Therefore, when the face region image under the backlight condition is heightened, the problem that the face skin color becomes light and has no blood color is avoided, the image quality is improved, meanwhile, the negative influence on the backlight region is avoided, and the visual effect of image display is ensured.

Description

Method and device for processing face area in backlight scene

technical field

The present invention relates to the technical field of image processing, and in particular, to a method and device for processing a face region of a backlight scene.

Background technique

Usually, when taking a photo, if the user's face is located between the light source and the camera, the exposure of the user's face to be photographed will be insufficient, resulting in a backlight effect. However, in the user's face image captured in this backlight scene, the brightness is very low, the user's face is dark, and the interview details are blurred.

In the related art, in order to improve the brightness of the face in the backlight scene, the ISO is raised very high to improve the brightness of the face area by enhancing the sensitivity to light. The noise level will also increase, which will cause the whole picture to be too bright, and the noise reduction will be too strong, which often leads to lighter skin tones, no blood, and poor visual effect of the image display.

SUMMARY OF THE INVENTION

The present invention provides a method and device for processing a face area in a backlight scene, so as to solve the problem of pale skin color in the face area caused by the increase in noise reduction intensity caused by only increasing the brightness of the face area in the backlight scene in the prior art. technical problem.

An embodiment of the present invention provides a method for processing a face area of a backlit scene, including: when a backlit scene is detected, separating a foreground and a backlit background from a current shooting picture; performing brightness enhancement processing on the foreground, and determining whether the foreground is in the foreground. face area; adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face area.

Another embodiment of the present invention provides a face area processing device for a backlight scene, including: a separation module for separating a foreground and a backlight background from a current shooting picture when a backlight scene is detected; a brightness enhancement module for The foreground is subjected to brightness enhancement processing; a determination module is used to determine the face area in the foreground; an adjustment module is used to adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face area .

Yet another embodiment of the present invention provides a terminal device, including one or more of the following components: a casing, a processor and a memory located in the casing, wherein the processor reads the available data stored in the memory by reading The program code is executed to run a program corresponding to the executable program code, so as to execute the method for processing a face region of a backlight scene according to the embodiment of the first aspect of the present invention.

Another embodiment of the present invention provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, realizes the face of the backlight scene according to the embodiment of the first aspect of the present invention area processing method.

The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

When a backlight scene is detected, the foreground and the backlight background are separated from the current shooting picture, the brightness of the foreground is improved, and the face area in the foreground is determined, and the preset CCM model parameters corresponding to the backlight scene are adjusted to improve the face. Saturation of the region. As a result, when the image of the face area in the backlight situation is raised, the problem that the skin color of the face becomes pale without blood color is avoided, and the image quality is improved, and the negative impact on the bright area is avoided, and the image display is guaranteed. visual effects.

Additional aspects and advantages of the present invention will be set forth, in part, from the following description, and in part will be apparent from the following description, or may be learned by practice of the invention.

Description of drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

1 is a flowchart of a method for processing a face region of a backlight scene according to an embodiment of the present invention;

2 is a schematic diagram of a backlight shooting scene according to an embodiment of the present invention;

FIG. 3(a) is a schematic diagram of the effect before processing the current captured image according to an embodiment of the present invention;

FIG. 3(b) is a schematic diagram of the effect of enhancing the brightness of the face area of the current shooting screen according to an embodiment of the present invention;

FIG. 3(c) is a schematic diagram of the effect of increasing the saturation of the current shooting image according to an embodiment of the present invention;

4 is a flowchart of a method for processing a face region of a backlight scene according to another embodiment of the present invention;

5 is a schematic structural diagram of an apparatus for processing a face region of a backlight scene according to an embodiment of the present invention;

6 is a schematic structural diagram of an apparatus for processing a face region of a backlight scene according to another embodiment of the present invention;

7 is a schematic structural diagram of an apparatus for processing a face region of a backlight scene according to yet another embodiment of the present invention; and

FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.

Detailed ways

The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention and should not be construed as limiting the present invention.

Based on the above analysis, it can be understood that in the related art, if the ISO sensitivity is increased, the sensitivity of the image sensor to light will be improved. Once the sensitivity to light is increased, the noise generated by environmental interference will also increase. Large, in order to reduce some irrelevant pixels in the image due to noise, the noise reduction intensity for the image will increase, but with the increase of the noise reduction intensity, some details of the image will be lost, making the face color in the face area change. Light, no blood, poor visual effect.

In order to solve the technical problem of the contradiction between improving the brightness of the face and losing the details of the face, the present invention proposes a method for processing the face area of the backlight scene, which can improve the brightness of the face area in the backlight scene and avoid the The details of the face are sacrificed to make the visual display of the image stronger.

The following describes a method and apparatus for processing a face region of a backlight scene according to embodiments of the present invention with reference to the accompanying drawings.

FIG. 1 is a flowchart of a method for processing a face region of a backlight scene according to an embodiment of the present invention. As shown in FIG. 1 , the method includes:

Step 101 , when a backlit scene is detected, the foreground and the backlit background are separated from the current shot.

It can be understood that, as shown in Figure 2, when the subject is between the light source and the camera, since the light travels in a straight line, there is strong light on the back of the subject and insufficient light on the front. The face area is relatively blurred, and the user is not satisfied with the rendering effect of the screen.

Therefore, in this embodiment, if the user does not want to change the shooting direction, in order to improve the brightness of the face region in a targeted manner, the location of the face region can be separated.

Specifically, after focusing on the photographed target object, the range of spatial depths allowed by the human eye for clear imaging before and after the focal area where the target object is located is the depth of field, wherein the range of clear imaging before the focal area is the foreground Depth of field, the position of the face area is in the foreground depth of field, the clear imaging range after the focus area is the background depth of field, and the backlight background is in the background depth of field. Therefore, in this example, the foreground and the backlight background are separated from the current shot according to the depth of field information. .

It should be noted that, according to different specific application scenarios, the methods of separating the foreground and the backlight background for the current shooting picture are different. Examples are as follows:

First example:

The relevant parameters of shooting can be obtained to calculate the depth of field information of the image area outside the focus area in the preview screen according to the formula of the shooting camera.

In this example, parameters such as the allowable circle of confusion diameter, aperture value, focal length, and focus distance of the camera can be obtained, so that according to the formula: foreground depth of field = (aperture value * allowable circle of confusion diameter * square of focus distance) / (focal length of Square + aperture value * allowable circle of confusion diameter * focus distance) to calculate the foreground depth of field, the foreground has been separated according to the foreground depth of field, and according to the formula background depth of field = (aperture value * allowable circle of confusion diameter * focus distance square) / (focal length of Square - aperture value * allowable circle of confusion diameter * focus distance) to calculate the depth of field of the backlight background, and then separate the backlight background according to the depth of field of the backlight background.

Second example:

Determine the depth of field map of the image area outside the focus area according to the current captured image data obtained by the dual cameras, determine the foreground depth of field before the focus area and the background depth of field after the focus area according to the depth of field map, and separate the foreground according to the foreground depth of field and the background depth of field. and backlit background.

Specifically, in this example, since the positions of the two cameras are not the same, the two rear cameras have a certain angle difference and distance difference with respect to the target object to be photographed, so the preview image data obtained by the two cameras is also different. There is a certain phase difference.

For example, for point A on the shooting target object, in the preview image data of camera 1, the coordinates of the pixel corresponding to point A are (30, 50), while in the preview image data of camera 2, the corresponding pixel coordinates of point A are The coordinates of the pixel point are (30, 48), and the phase difference of the corresponding pixel point of point A in the two preview image data is 50-48=2.

In this example, the relationship between the depth of field information and the phase difference can be established in advance according to the experimental data or camera parameters, and further, the corresponding depth of field information can be searched according to the phase difference of each image point in the preview image in the preview image data obtained by the two cameras .

For example, for the above-mentioned phase difference 2 corresponding to point A, if the corresponding depth of field is 5 meters according to the preset correspondence query, the depth of field information corresponding to point A in the preview screen is 5 meters. In this way, the depth of field information of each pixel in the current preview image can be obtained, that is, the depth of field map of the image area other than the focus area can be obtained.

Furthermore, after obtaining the depth-of-field map of the image area outside the focus area, the foreground depth-of-field information of the image area before the focus area and the background depth-of-field information after the focus area can be further determined, so that the foreground before the focus area is determined according to the depth-of-field map The depth of field and the background depth of field behind the focus area, and the foreground and backlit background are separated according to the foreground depth of field and the background depth of field.

Step 102 , perform brightness enhancement processing on the foreground, and determine the face area in the foreground.

It can be understood that the brightness of the face area in the backlight scene and other areas in the foreground are low, and the boundaries of the face area are blurred compared to other areas. Therefore, at this time, the brightness enhancement process is performed on the foreground. The brightness of the face region is improved, so that the face is clearly visible, and the boundary of the face region is clearer than other regions, which facilitates the extraction of the face region for further processing of the face region.

Among them, in different application scenarios, different implementation methods can be used to realize the determination of the face area in the foreground, and examples are as follows:

First example:

The color of the face area in the foreground is different from other areas. The face area is the color of the human body such as skin color, while the other area is the color of other scenes that are different from the color of the face area. Therefore, the color channel detection algorithm can be used. , identify the area where the skin color is located to determine the contour edge of the face area in the foreground according to the area covered by the skin color.

Second example:

Due to the discontinuity of the image edge, such as the sudden change of gray level, the sudden change of color and the sudden change of texture structure, this edge exists between the object and the background. Therefore, in this example, this characteristic of the image edge is used. , through the CANNY algorithm, wavelet transform algorithm and other image edge detection algorithms to determine the contour edge of the face area in the foreground.

Step 103: Adjust preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face region.

As analyzed above, when the brightness of the face area is increased, the facial fineness in the face area will be lost, so that the pale face loses its blood color, and the loss of blood color in the pale face is actually reflected in the low saturation of the face area. Degree refers to the vividness of the color, also known as the purity of the color. The saturation of the face area depends on the proportion of the color component and the achromatic component (gray) in the face area. The larger the color component, the smaller the saturation.

Therefore, if the saturation of the face is increased, the color components in the face area will be increased, so that the face area will be rosy and shiny.

Specifically, in the embodiment of the present invention, the adjustment of saturation is realized based on the adjustment of the parameters of the CCM model.

Among them, the calculation formula of the CCM model (Color Color Matrix, color correction matrix) is shown in the following formula (1):

CCM之后的像素为 Among them, the pixel before CCM is

The pixels after CCM are

因此，CCM之后的像素为可以表示为：

基于以上对应关系可知，可以通过改变CCM模型矩阵中对角线上的参数C00、C11、C22的值实现对RGB颜色分配的调整，从而实现对饱和度的调整。That is to say, the implementation of CCM is based on a simple linear matrix. The coefficients of RG and BG are adjusted in the G path, the coefficients of GR and BR are adjusted in the R path, and the coefficients of GB and RB can be adjusted in the B path. Correction to change the color tone of the picture. Among them, the CCM model should not affect the white balance when performing color correction, because the gain of each camera device is adjusted according to the white balance condition, that is, when capturing a white scene, the amplitudes of the three outputs R, G, and B should be equal. That is to say, the corrected three primary colors should keep R=G=B. According to this relationship, the relationship of each coefficient in the above formula (1) is as follows:

So the pixel after CCM is It can be expressed as:

Based on the above correspondence, it can be known that the adjustment of the RGB color distribution can be realized by changing the values of the parameters C00, C11, and C22 on the diagonal line in the CCM model matrix, thereby realizing the adjustment of the saturation.

However, in practical applications, when the CCM model parameters are used to improve the saturation of the entire picture, the saturation of the smooth light area in the picture is also improved, which may cause color distortion in the smooth light area, etc., affecting the smooth light area. display effect.

Therefore, in the embodiment of the present invention, the saturation of the photographed object in the backlit scene and the frontlit scene are detected respectively, the CCM model parameters corresponding to the backlit scene are set according to the detection results, and the preset CCM model parameters corresponding to the backlit scene are adjusted to improve the Saturation of face areas in backlight.

Among them, it should be understood that the above-mentioned CCM model parameters are set for the backlight scene, so in the actual adjustment process, the saturation of the front light area does not change, and the implementation of the CCM model parameters can only be used in the backlight area. The function of the face area. Since the setting of the CCM model parameters is strongly related to the color temperature and brightness of the picture color, in order to avoid the adjustment of the CCM model parameters to the front light area during the implementation process, the above settings correspond to the CCM model parameters of the backlight scene. , is set based on the same color temperature and brightness of the backlight scene and the front light scene.

It should be emphasized that, in the example of the present invention, in the backlight scene, the method based on depth information is used to extract the face area, which is more accurate than the direct face recognition to obtain the face area. In the backlight scene, the brightness of the face area is low and the features are not obvious. It is very likely that the face recognition will fail directly.

Therefore, in the method for processing a face region of a backlight scene according to the embodiment of the present invention, after improving the brightness of the face, the saturation of the face region is adjusted based on the adjustment of the parameters of the CCM model, and the color content of the face region is improved, Makes the face rosy and shiny. And when the saturation is adjusted based on the CCM model parameters, since the CCM model parameters are set based on the backlight scene, in the adjustment process, the saturation adjustment is only performed on the face area in the backlight scene. That is, for the backlight scene alone, set a set of CCM model parameters, so that the CCM model parameters of the backlight scene are separated from the normal scene, so as to avoid the negative impact on the smooth area of the picture due to the increase of the saturation of the backlight scene during the debugging process.

In order to more clearly reflect the face area processing flow of the backlight scene, the following example illustrates that when the backlight scene as shown in Figure 3(a) is detected, the foreground and the backlight background are separated from the current shooting picture, and then the foreground is processed. Brightness enhancement processing, as shown in Figure 3(b), the brightness of the processed face is improved, but the facial details are lost. Furthermore, the preset CCM model parameters corresponding to the backlight scene are adjusted to improve the saturation of the face area, then As shown in Figure 3(c), the face of the human face is rosy and shiny, and the brightness is improved, while the saturation of the smooth area is not negatively affected.

To sum up, according to the method for processing a face region of a backlight scene according to the embodiment of the present invention, when a backlight scene is detected, the foreground and the backlight background are separated from the current shooting picture, the brightness of the foreground is enhanced, and the face in the foreground is determined. area, and adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face area. As a result, when the image of the face area in the backlight situation is raised, the problem that the skin color of the face becomes pale without blood color is avoided, and the image quality is improved, and the negative impact on the bright area is avoided, and the image display is guaranteed. visual effects.

Based on the above embodiments, it should be understood that in different application scenarios, the darkening degree of the face area is different due to the difference in the intensity of the ambient light of the backlight. The stronger the ambient light, the darker the face area and the darker the ambient light. Not strong, the brighter the face area, the darker the face area, the more facial details are lost, and the degree of saturation needs to be improved. Therefore, in order to improve the processing effect of increasing the saturation of the face area, according to the current environment Adjust the saturation of the backlight intensity.

As shown in Figure 4, the above step 103 includes:

Step 201, detecting the backlight intensity of the current scene.

It should be understood that the higher the light intensity on the user's back when taking pictures, the higher the backlight intensity of the current scene, and the darker the foreground where the user's face area is.

The method of detecting the backlight intensity of the current scene may vary according to the specific application scenario, for example, obtaining the backlight intensity sensed by the photosensitive element in the camera module, for example, calculating the backlight intensity according to the brightness of the foreground, etc.

Step 202, acquiring the enhancement magnitude corresponding to the backlight intensity.

Among them, the enhancement amplitude corresponds to the saturation enhancement amplitude, the higher the enhancement amplitude, the greater the saturation enhancement amplitude, and vice versa, the lower the enhancement amplitude, the smaller the saturation enhancement amplitude.

It should be noted that, according to different application scenarios, a variety of different implementation methods can be used to obtain the enhancement amplitude corresponding to the backlight intensity. After the backlight intensity is obtained, the above corresponding relationship is queried to obtain the corresponding enhancement magnitude. As another possible implementation manner, a conversion function is generated according to the relationship between the backlight intensity and the enhancement amplitude, so that after obtaining the backlight intensity, the corresponding enhancement amplitude is obtained through the conversion function.

Step 203: Adjust preset CCM model parameters corresponding to the backlight scene according to the enhancement magnitude to improve the saturation of the face region.

Specifically, according to the enhancement range consistent with the backlight intensity in the current scene, the parameters of the CCM model are adjusted to increase the saturation corresponding to the face area, so that the face area will not be over-saturated or under-saturated. The processing effect is good. The CCM model parameters only increase the saturation of the face area in the backlight scene, avoiding the negative impact on the front light area.

Of course, in practical applications, the skin color of each part of the human face is also different. For example, under normal circumstances, the cheeks of the human face are more rosy than the forehead, etc. Therefore, in order to further improve the processing effect, different face regions can also be The parts determine different saturation coefficients, so as to implement different degrees of saturation adjustment for different parts of the face region according to the different saturation coefficients.

Specifically, the saturation adjustment coefficients corresponding to different parts of the face area are obtained, wherein in reality, the more ruddy parts have higher saturation coefficients. The improvement range corresponding to the part, according to the improvement range corresponding to different parts, adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the corresponding position in the face area.

To sum up, in the method for processing a face region of a backlight scene according to the embodiment of the present invention, the enhancement amplitude is determined according to the backlight intensity of the current scene, and the preset CCM model parameters corresponding to the backlight scene are adjusted according to the enhancement amplitude to improve the saturation of the face region. Spend. Therefore, an appropriate enhancement amplitude is selected for the face region to be processed to improve the saturation, so as to avoid over-saturation or under-saturation of the face region, and further improve the visual effect of image display.

In order to realize the above-mentioned embodiment, the present invention also proposes an apparatus for processing a face area of a backlight scene. FIG. 5 is a schematic structural diagram of an apparatus for processing a face area of a backlit scene according to an embodiment of the present invention, as shown in FIG. 5 , The apparatus for processing the face area of the backlight scene includes: a separation module 100 , a brightness enhancement module 200 , a determination module 300 and an adjustment module 400 .

Wherein, the separation module 100 is configured to separate the foreground and the backlight background from the current shooting picture when a backlight scene is detected.

In an embodiment of the present invention, as shown in FIG. 6 , the separation module 100 includes a first acquisition unit 110 , a determination unit 120 and a separation unit 130 .

The first obtaining unit 110 is configured to determine a depth map of an image area other than the focus area according to the current shooting picture data obtained respectively by the dual cameras.

The determining unit 120 is configured to determine, according to the depth map, a foreground depth of field before the focus area and a background depth of field after the focus area.

The separation unit 130 is configured to separate the foreground and the backlight background according to the foreground depth of field and the background depth of field.

The brightness enhancement module 200 is used for performing brightness enhancement processing on the foreground.

The determining module 300 is used for determining the face area in the foreground.

The adjustment module 400 is configured to adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face area.

It should be noted that the foregoing explanations of the method for processing a face region in a backlight scene are also applicable to the device for processing a face region in a backlight scene according to the embodiment of the present invention, and the implementation principles thereof are similar, which will not be repeated here.

To sum up, the apparatus for processing a face area of a backlight scene according to the embodiment of the present invention, when a backlight scene is detected, separates the foreground and the backlight background from the current shooting picture, performs brightness enhancement processing on the foreground, and determines the face in the foreground. area, and adjust the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face area. As a result, when the image of the face area in the backlight situation is raised, the problem that the skin color of the face becomes pale without blood color is avoided, and the image quality is improved, and the negative impact on the bright area is avoided, and the image display is guaranteed. visual effects.

FIG. 7 is a schematic structural diagram of face region processing in a backlight scene according to another embodiment of the present invention. As shown in FIG. 7 , on the basis of FIG. 5 , the adjustment module 400 includes a detection unit 410 and a second acquisition unit. 420 and adjustment unit 430.

Among them, the detection unit 410 is used to detect the backlight intensity of the current scene.

The second obtaining unit 420 is configured to obtain the enhancement magnitude corresponding to the backlight intensity.

The adjustment unit 430 is configured to adjust the preset CCM model parameters corresponding to the backlight scene according to the enhancement magnitude to improve the saturation of the face region.

It should be noted that the foregoing explanations of the method for processing a face region in a backlight scene are also applicable to the device for processing a face region in a backlight scene according to the embodiment of the present invention, and the implementation principles thereof are similar, which will not be repeated here.

To sum up, the apparatus for processing a face area of a backlight scene according to the embodiment of the present invention determines the enhancement range according to the backlight intensity of the current scene, and adjusts the preset CCM model parameters corresponding to the backlight scene according to the enhancement range to improve the saturation of the face area. Spend. Therefore, an appropriate enhancement amplitude is selected for the face region to be processed to improve the saturation, so as to avoid over-saturation or under-saturation of the face region, and further improve the visual effect of image display.

In order to implement the above embodiments, the present invention further provides a terminal device, and FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present invention. As shown in FIG. 8 , the terminal device 1000 includes: a casing 1100 , a processor 1110 and a memory 1120 located in the casing 1100 , wherein the processor 1110 runs and executes executable program codes stored in the memory 1120 by reading the executable program codes stored in the memory 1120 . A program corresponding to the program code is executed, so as to execute the method for processing a face region of a backlight scene described in the foregoing embodiments.

In order to realize the above-mentioned embodiments, the present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the person who can realize the backlight scene as described in the foregoing embodiments face area processing method.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing custom logical functions or steps of the process , and the scope of the preferred embodiments of the invention includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions substantially concurrently or in the reverse order depending upon the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present invention belong.

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, may be embodied in any computer-readable medium, For use with, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions from an instruction execution system, apparatus, or apparatus) or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or apparatus. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of the present invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one of the following techniques known in the art, or a combination thereof: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those skilled in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present invention have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present invention. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (8)

1. A method for processing a face region of a backlit scene, comprising:

when a backlight scene is detected, acquiring current shooting pictures respectively shot by the two cameras;

determining a depth of field map of an image area outside a focus area according to the phase difference of the shooting pictures obtained by the two cameras at each image point in the current shooting picture;

determining a foreground depth of field before the focal region and a background depth of field after the focal region from the depth of field map;

separating a foreground background and a backlight background according to the foreground depth of field and the background depth of field;

performing brightness improvement processing on the foreground, and determining a face area in the foreground after brightness improvement;

and adjusting the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face region.

2. The method of claim 1, further comprising:

for the same color temperature and brightness, detecting the saturation of the shot object under a backlight scene and a frontlight scene respectively;

and setting CCM model parameters corresponding to the backlight scene according to the detection result.

3. The method of claim 1, wherein said adjusting CCM model parameters corresponding to said backlit scene to increase saturation of said face region comprises:

detecting the backlight intensity of the current scene;

obtaining an enhancement amplitude corresponding to the backlight intensity;

and adjusting the preset CCM model parameters corresponding to the backlight scene according to the enhancement amplitude to improve the saturation of the face region.

4. The method of claim 3, wherein the adjusting the preset CCM model parameters corresponding to the backlight scene according to the enhancement amplitude to improve the saturation of the face region comprises:

acquiring saturation adjustment coefficients corresponding to different parts of the human face area;

calculating the lifting amplitude corresponding to the different parts according to the saturation adjustment coefficients corresponding to the different parts and the enhancement amplitude;

and adjusting preset CCM model parameters corresponding to the backlight scene according to the lifting ranges corresponding to the different parts to improve the saturation of the corresponding position of the face region.

5. A face region processing apparatus for a backlit scene, comprising:

a separation module, the separation module comprising: the device comprises a first acquisition unit, a determination unit and a separation unit;

the first acquisition unit is used for acquiring current shooting pictures respectively shot by the two cameras, and determining a depth-of-field map of an image area outside a focus area according to the phase difference of each image point in the current shooting pictures obtained by the two cameras in the shooting pictures;

the determining unit is used for determining the foreground depth of field before the focus area and the background depth of field after the focus area according to the depth of field map;

the separation unit is used for separating a foreground background and a backlight background according to the foreground field depth and the background field depth;

the brightness improving module is used for improving the brightness of the foreground;

the determining module is used for determining the face area in the foreground after brightness improvement;

and the adjusting module is used for adjusting the preset CCM model parameters corresponding to the backlight scene to improve the saturation of the face region.

6. The apparatus of claim 5, wherein the adjustment module comprises:

the detection unit is used for detecting the backlight intensity of the current scene;

a second acquisition unit configured to acquire an enhancement amplitude corresponding to the backlight intensity;

and the adjusting unit is used for adjusting the preset CCM model parameters corresponding to the backlight scene according to the enhancement amplitude to improve the saturation of the face region.

7. A terminal device, comprising: the backlight scene comprises a shell, and a processor and a memory which are positioned in the shell, wherein the processor executes a program corresponding to an executable program code by reading the executable program code stored in the memory so as to execute the face area processing method of the backlight scene as claimed in any one of claims 1 to 4.

8. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for processing a face region of a backlit scene as recited in any of claims 1-4.

Images