WO2022105270A1

WO2022105270A1 - Image processing method and apparatus

Info

Publication number: WO2022105270A1
Application number: PCT/CN2021/106299
Authority: WO
Inventors: 李乐; 秦文煜; 刘晓坤; 陶建华; 鹿镇
Original assignee: 北京达佳互联信息技术有限公司
Priority date: 2020-11-17
Filing date: 2021-07-14
Publication date: 2022-05-27
Also published as: CN112381737B; CN112381737A

Abstract

An image processing method and apparatus, and an electronic device and a storage medium, which are used to improve a facial de-glossing effect in a facial image. The method comprises: acquiring a facial image, and determining a facial region in the facial image (S100); inputting the facial image into an attribute information extraction model so as to obtain facial attribute information of the facial region and environmental attribute information of the facial image (S101); performing region extraction on the facial region according to the facial attribute information and the environmental attribute information so as to obtain a glossy region in the facial region (S103); and performing a de-glossing treatment on the glossy region according to the facial attribute information and the environmental attribute information so as to obtain a de-glossed facial image (S104).

Description

Image processing method and device

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of Chinese patent application No. 202011287995.6 filed on November 17, 2020. The contents disclosed in the above Chinese patent application are hereby cited in their entirety as a part of this application.

technical field

The present disclosure relates to the technical field of image processing, and in particular, to an image processing method and apparatus.

Background technique

In the process of collecting face images, due to factors such as lighting, it is easy to include oily areas in the collected face images, resulting in poor human figures in the images. Degrease treatment.

At present, the facial degreasing technology mainly includes: first, obtaining the brightness value of each pixel point in the face image; then, determining the difference value between the brightness value of each pixel point and the preset brightness value, and finally, according to the determined difference value The value determines the glossy areas in the face image and de-glosses the glossy areas.

SUMMARY OF THE INVENTION

The present disclosure provides an image processing method, an apparatus, an electronic device and a storage medium, so as to improve the effect of de-grease of the face in the face image.

The technical solutions of the present disclosure are as follows:

According to a first aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide an image processing method, the method includes: acquiring a face image, and determining a face area in the face image; inputting the face image into an attribute information extraction model ; Obtain the facial attribute information of the face area and the environmental attribute information of the face image; According to the facial attribute information and the environmental attribute information, the area extraction is carried out on the face area to obtain the oily area in the face area; According to the facial attribute information and Environmental attribute information, and de-gloss processing is performed on the glossy area to obtain a de-glossy face image.

In the embodiment of the present disclosure, in the process of determining the glossy area and performing de-gloss processing on the glossy area, the facial attribute information and the environmental attribute information are referred to, so that the glossy area can be determined more accurately and the glossy area can be appropriately processed, thereby improving the The effect of de-glossing the face in the face image.

In an implementation manner, the facial attribute information includes at least one of skin color, skin texture, brightness or age of the human face in the face region; and the environmental attribute information includes at least ambient lighting information.

The skin color, skin texture, brightness or age of the face, and ambient lighting information directly affect the average brightness value of each pixel in the face, so the oily area determined based on these information is more accurate.

In another implementation manner, the above-mentioned step of performing region extraction on the face region according to the face attribute information and the environmental attribute information to obtain the oily region in the face region includes: obtaining the first region according to the face attribute information and the environmental attribute information Adjustment coefficient; increase the brightness value of each pixel in the face image according to the first adjustment coefficient; determine the oily area in the face area according to the face area after the increased brightness value.

In this way, after increasing the brightness value of each pixel in the face image to the same standard, the oily area in the face area can be determined according to the preset standard, and the facial attribute information and the environmental attribute information directly affect the adjustment of the brightness value The first adjustment factor of . Therefore, after determining the first adjustment coefficient according to the facial attribute information and the environmental attribute information, and adjusting the face image, the determined oily area is more accurate.

In another implementation manner, the above-mentioned step of obtaining the first adjustment coefficient according to the facial attribute information and the environmental attribute information includes: inputting the facial attribute information and the environmental attribute information into the adjustment coefficient extraction function to obtain the first adjustment coefficient; The function is obtained by linear regression analysis based on the adjustment coefficients, facial attribute information and environmental attribute information marked in multiple sample face images.

In this way, the linear regression analysis is performed on the adjustment coefficients, facial attribute information and environmental attribute information marked in the multiple sample face images, and the interdependence between the adjustment coefficients, the facial attribute information and the environmental attribute information can be obtained. The marked adjustment coefficient, facial attribute information, and environmental attribute information can be determined according to the values when the sample image is manually processed to achieve the expected effect. Therefore, the first adjustment coefficient calculated according to the adjustment coefficient extraction function has a higher probability to achieve the expected effect after adjusting the face image.

In another implementation manner, the above-mentioned step of increasing the brightness value of each pixel in the face image according to the first adjustment coefficient includes: converting the color space of the face image into a target color space; the target color space includes representing a face The information of the brightness value of the pixel point in the image; the brightness value of each pixel point in the face image in the target color space is increased according to the first adjustment coefficient.

In another implementation manner, the above-mentioned step of determining the oily area in the face area according to the increased brightness value of the face area includes: setting the brightness value in the increased brightness value of the face area to be greater than the first preset value The area composed of threshold pixels is determined as the oily area in the face area.

In another implementation manner, the oily area in the above-mentioned face area satisfies the following formula: M=pow(Y,s), where M is the oily area in the face area, pow is an exponential function; Y is the increase in brightness The brightness value of each pixel in the face area after the value, s is the coefficient of the exponential function; and s is obtained by inputting the facial attribute information and environmental attribute information into the exponential coefficient calculation function; the exponential coefficient calculation function is based on multiple samples The index coefficient, facial attribute information and environmental attribute information of face image annotation are obtained by linear regression analysis.

In another implementation manner, the above-mentioned step of performing de-gloss processing on the glossy area according to the facial attribute information and the environmental attribute information includes: inputting the facial attribute information and the environmental attribute information into the dimming coefficient calculation function to obtain the facial image Darkening coefficient; the darkening coefficient calculation function is obtained by linear regression based on the darkening coefficient, facial attribute information and environmental attribute information marked in multiple face images; reduce each pixel in the oily area according to the darkening coefficient of the face image The brightness value of the point.

In another implementation manner, the method further includes: fusing the face image with the de-glossed face image to obtain the target image.

In this way, the fused image takes into account the details in the face image and the effect of degreasing.

In another implementation manner, the above-mentioned step of performing region extraction on the face region to obtain the shiny region in the face region according to the face attribute information and the environmental attribute information includes: performing skin grinding on the face region; information and environmental attribute information, and extract the area of the face area after microdermabrasion to obtain the shiny area in the face area.

In this way, before determining the oily area, microdermabrasion on the face area can initially reduce part of the oily gloss, so that the final oily gloss removal effect is better.

According to a second aspect of the embodiments of the present disclosure, the embodiments of the present disclosure provide an image processing apparatus, including: an acquisition module configured to acquire a face image and determine a face area in the face image; an extraction module configured to In order to input the face image into the attribute information extraction model; obtain the face attribute information of the face area and the environmental attribute information of the face image; according to the face attribute information and the environmental attribute information, extract the face area to obtain the face area The oily area in the ; the de-gloss module is configured to perform de-gloss processing on the glossy area according to the facial attribute information and the environmental attribute information, so as to obtain the de-gloss face image.

In some embodiments, the facial attribute information includes at least one of skin color, skin texture, brightness, or age of the human face in the face region; and the environmental attribute information includes at least ambient lighting information.

In some embodiments, the acquiring module is further configured to: acquire a first adjustment coefficient according to the facial attribute information and the environmental attribute information; the extracting module is specifically configured to: increase the brightness of each pixel in the face image according to the first adjustment coefficient value; according to the face area after increasing the brightness value, determine the oily area in the face area.

In some embodiments, the acquisition module is further configured to input the facial attribute information and the environmental attribute information into an adjustment coefficient extraction function to obtain a first adjustment coefficient; the adjustment coefficient extraction function is based on adjustments marked in a plurality of sample face images coefficients, facial attribute information and environmental attribute information obtained by linear regression analysis.

In some embodiments, the image processing apparatus further includes an augmentation module configured to: convert the color space of the face image into a target color space; the target color space includes information representing luminance values of pixels in the face image; The brightness value of each pixel in the face image in the target color space is increased according to the first adjustment coefficient.

In some embodiments, the extraction module is further configured to: determine an area composed of pixels whose brightness value is greater than the first preset threshold in the face region after the brightness value has been increased as a glossy region in the face region.

In some embodiments, the oily area in the face area satisfies the following formula: M=pow(Y,s), where M is the oily area in the face area, pow is an exponential function; Y is the value after increasing the brightness value The brightness value of each pixel in the face area of , s is the coefficient of the exponential function; and s is obtained by inputting facial attribute information and environmental attribute information into the exponential coefficient calculation function; The exponential coefficient of image annotation, facial attribute information and environmental attribute information are obtained by linear regression analysis.

In some embodiments, the degreasing module is further configured to: input the facial attribute information and the environmental attribute information into a dimming coefficient calculation function to obtain a dimming coefficient of the face image; the dimming coefficient calculation function is based on a plurality of face images It is obtained by linear regression of the dimming coefficient, facial attribute information and environmental attribute information marked in the face image; the brightness value of each pixel in the oily area is reduced according to the dimming coefficient of the face image.

In some embodiments, the image processing apparatus further includes a fusion module configured to fuse the face image with the de-glossed face image to obtain the target image.

In some embodiments, the extraction module is further configured to: perform microdermabrasion processing on the face area; perform area extraction on the microdermabrasion processed face area according to the facial attribute information and the environmental attribute information, so as to obtain the facial area in the face area. oily areas.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing instructions executable by the processor. The processor is configured to execute the instructions to implement the image processing method shown in the first aspect and any implementation manner of the first aspect.

According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the image processing method shown in the first aspect .

According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, which can be directly loaded into an internal memory of an electronic device and contains software codes, and after the computer program is loaded and executed by the electronic device, can realize the above-mentioned first aspect. The image processing method shown.

Any image processing device, electronic device or computer-readable storage medium or computer program product provided above is used to execute the corresponding method provided above, therefore, it is possible to determine the glossy area and carry out de-gloss processing to the glossy area. During the process, referring to the facial attribute information and the environmental attribute information, it is possible to appropriately process the glossy area, thereby improving the effect of removing the glossiness of the face in the face image.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the principles of the present disclosure and do not unduly limit the present disclosure.

FIG. 1 is a schematic flowchart of an image processing method according to an exemplary embodiment;

FIG. 2 is a schematic diagram of a human face key point according to an exemplary embodiment;

3 is a block diagram of an image processing apparatus according to an exemplary embodiment;

Fig. 4 is a block diagram of an electronic device according to an exemplary embodiment.

Detailed ways

In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that, in the embodiments of the present disclosure, words such as "exemplary" or "such as" are used to represent examples, illustrations, or illustrations. Any embodiments or designs described in the embodiments of the present disclosure as "exemplary" or "such as" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present the related concepts in a specific manner.

It should be noted that the terms "first", "second" and the like in the description and claims of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.

The data involved in this disclosure may be data authorized by the user or fully authorized by all parties.

In the embodiments of the present disclosure, "at least one" refers to one or more. "Plural" means two or more.

In this embodiment of the present disclosure, "and/or" is only an association relationship describing associated objects, indicating that there may be three kinds of relationships, for example, A and/or B, which may indicate that A exists alone, and A and B exist at the same time. B, there are three cases of B alone. In addition, the character "/" in this document generally indicates that the related objects are an "or" relationship.

In an embodiment of the present disclosure, a composition includes one or more objects.

It should be noted that the image processing method provided by the embodiments of the present disclosure may be applied to an electronic device or a server. Among them, electronic devices include but are not limited to mobile phones, tablet computers, notebook computers, handheld computers, vehicle terminals, and the like. The server may be one server, or may also be a server cluster composed of multiple servers, which is not limited in the present disclosure.

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

As shown in FIG. 1 , FIG. 1 is a schematic flowchart of an image processing method according to an exemplary embodiment. The method shown in FIG. 1 can be applied to an electronic device or a server. The method shown in Figure 1 may include the following steps:

In S100, a face image is acquired, and a face region in the face image is determined.

The present disclosure does not limit the manner of acquiring a face image including a human face. In one implementation manner, a face image sent by other electronic devices is received, and in another implementation manner, a face image uploaded by a user is acquired, In another implementation manner, a local face image is read, and in another implementation manner, the face image is collected by a collection device integrated in an electronic device.

In an example, the execution subject is an electronic device, and the electronic device is an electronic device including a capture device such as a camera, and the camera of the electronic device captures a face image in the current environment. Among them, the lighting information of the current environment is certain.

In an implementation manner, determining the face region in the face image includes the following steps:

Step 1: Obtain the key points of the face in the face image.

In an example, the key points of the face are obtained using the trained face key point detection model as shown in Figure 2. The white dots in Figure 2 are the detected face key points.

Step 2: Determine the face area in the face image according to the acquired key points.

Based on the example of face key points in FIG. 2 , the closed area formed by connecting the acquired key points is the face area in the face image shown in FIG. 2 .

In another implementation, the face region in the face image is determined based on skin color detection.

Specifically, after binarizing the face region and the non-face region of the face image, the face region in the face image is determined.

In one example, a histogram method is used to determine a binarization threshold, the face image is binarized by using the binarization threshold, and then a face region is determined in the binarized face image.

It should be noted that the determination of the face region in the face image in the present disclosure may also be other methods in the prior art, which are not limited in the present disclosure.

In S101, the face image is input into the attribute information extraction model to obtain the face attribute information of the face region and the environmental attribute information of the face image.

The attribute information extraction model may be trained in advance based on sample face images; the facial attribute information includes at least one of skin color, skin texture, brightness or age of the face in the face area; the environmental attribute information includes at least ambient lighting information.

The skin color, skin quality, brightness or age of the face, and ambient lighting information directly affect the average brightness value of each pixel in the face. The results are more accurate.

In some embodiments, in S102, the facial area in the facial image is subjected to skin resurfacing processing.

In some embodiments, an edge-preserving filter may be used to perform skin resurfacing on the face region in the face image.

This embodiment of the present disclosure does not limit the edge-preserving filter used. Exemplarily, the edge-preserving filter may be: a bilateral filter, a guided image filter, a weighted least squares filter ( Weighted least square filter) and other edge-preserving filters.

In S103, region extraction is performed on the face region according to the face attribute information and the environment attribute information, so as to obtain a glossy region in the face region.

In some embodiments, the oily area in the face area is extracted by the following steps:

In step 1, the first adjustment coefficient of the face image is obtained according to the face attribute information and the environment attribute information.

In some embodiments, the facial attribute information and the environmental attribute information are input into the adjustment coefficient extraction function for operation to obtain the first adjustment coefficient. The adjustment coefficient extraction function is obtained by linear regression analysis based on the adjustment coefficients, facial attribute information and environmental attribute information marked in the multiple sample face images.

It can be understood that the marked adjustment coefficient, facial attribute information and environmental attribute information can be determined according to the adjustment coefficient, facial attribute information and environmental attribute information when the sample image is manually processed to achieve the expected effect. Therefore, the first adjustment coefficient calculated according to the adjustment coefficient extraction function has a higher probability to achieve the expected effect after adjusting the face image.

In step 2, the brightness value of each pixel in the face image is increased according to the first adjustment coefficient.

In some embodiments, before adjusting the luminance value of each pixel in the face image, if the color space of the face image is the color space used for display, the color space of the face image may be converted to include a luminance component The color space, in one example, converts a face image in the red (R), green (G), blue (B) color space to any of the YUV color space, HSI color space, HSV color space, or Lab color space A sort of. Then, use the first parameter to adjust the brightness value of each pixel in the face image.

In one example, the first parameter is used to increase the brightness value of each pixel in the face image according to the same algorithm. If the brightness value of the pixel point after the brightness value is increased is greater than 1, the brightness value of the pixel point is determined as 1; if the brightness value of the pixel point after the brightness value is increased is less than 1, the brightness value of the pixel point after the brightness value is increased The brightness value of the pixel is taken as the brightness value of the pixel.

In some embodiments, step three is further included. In step 3, an exponential operation is performed on the brightness value of each pixel in the face image increased by the first parameter according to the second parameter. Among them, the second parameter is obtained by inputting the facial attribute information and environmental attribute information of the face image into the exponential coefficient calculation function; the exponential coefficient calculation function is obtained according to the exponential coefficient, facial attribute information and environmental attribute information marked on multiple sample face images obtained by linear regression analysis.

In one example, the second parameter is used as an exponent to perform exponentiation on the luminance value of each pixel in the face image adjusted by using the first parameter. Assuming that the second parameter is 10, and the brightness value of the first pixel in the face image adjusted by the first parameter is 0.5, then, using 10 as an exponent, the brightness value of the first pixel is obtained by exponentiating 0.5. The new luminance value can be expressed as: (0.5) ¹⁰ with the formula.

In some embodiments, step four is also included. In step 4, in the case where step 3 is not performed, the area composed of pixels whose brightness value is greater than the first preset threshold in the face area after the adjustment of the brightness value is determined as the oily area in the face area.

In the case where step 3 is performed, in the face image after the exponential operation, the area composed of pixels whose brightness value is greater than the second preset threshold is determined as the oily area in the face area.

The oily area in the face area satisfies the following formula:

M=pow(Y,s)

Among them, M is the oily area in the face area, pow is the exponential function; Y is the brightness value of each pixel in the face area after increasing the brightness value, and s is the coefficient of the exponential function. s can be obtained by inputting the facial attribute information of the face image and the environmental attribute information into the exponential coefficient calculation function. The exponential coefficient calculation function is obtained based on the linear regression analysis of the exponential coefficient, facial attribute information and environmental attribute information annotated by multiple sample face images.

In S104 , according to the facial attribute information and the environmental attribute information, de-gloss processing is performed on the glossy area to obtain an image of the de-glossy face.

In some embodiments, the facial attribute information and the environmental attribute information of the face image are input into a dimming coefficient calculation function to obtain a dimming coefficient of the face image, and the dimming coefficient of the face image is used to reduce the shading coefficient of each face image in the oily area. The luminance value of a pixel. The dimming coefficient calculation function can be obtained by linear regression analysis based on the dimming coefficients, facial attribute information and environmental attribute information marked on multiple sample face images.

In one example, the dimming factor can be a percentage less than 1, and the dimming factor is used to multiply the brightness value of each pixel in the oily area to obtain a new brightness value corresponding to each pixel, using the new brightness The value replaces the original brightness value of the pixel to obtain a de-glossy face image. In another example, the brightness value of each pixel in the oily area is subtracted by the dimming coefficient to obtain a new brightness value of each pixel, and the original brightness value of the pixel is replaced with the new brightness value to obtain the Oily face image.

In the embodiment of the present disclosure, in the process of determining the glossy area and performing de-gloss processing on the glossy area, the facial attribute information and the environmental attribute information are referred to, so that the glossy area can be appropriately processed, thereby improving the human face in the image. The effect of removing oil on the face.

In some embodiments, in S105 , the face image after dermabrasion processing of the face region is mixed with the degreasing face image to obtain the target image.

In some embodiments, the face image after the skin-removed face region is fused with the degreasing face image to obtain the target image. Based on the alpha channel, or using the feathering operation, the face image after microdermabrasion processing and the de-gloss face image can be fused.

It can be understood that the original face image and the degreasing face image can also be fused to obtain the target image. The effect of the target image obtained in this way is worse than the target image obtained by fusing the face image after the skin-grinding process with the de-gloss face image.

In this way, the obtained target image has both the details of the face image after the skin-grinding process and the de-gloss effect of the de-glossy face image.

The foregoing mainly introduces the solutions provided by the embodiments of the present disclosure from the perspective of methods. In order to realize the above-mentioned functions, it includes corresponding hardware structures and/or software modules to perform each function. Those skilled in the art should readily appreciate that the present disclosure can be implemented in hardware or in a combination of hardware and computer software, in conjunction with the method steps of the examples described in the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this disclosure.

In the embodiments of the present disclosure, the image processing apparatus can be divided into functional modules according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing 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. It should be noted that, the division of modules in the embodiments of the present disclosure is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

Fig. 3 is a block diagram of an image processing apparatus according to an exemplary embodiment. Referring to FIG. 4 , the image processing apparatus 200 includes an acquisition module 201 , an extraction module 202 and a degreasing module 203 . Optionally, the image processing apparatus 200 further includes an enlargement module 204 and a fusion module 205 . Wherein: the acquisition module 201 is configured to acquire a face image and determine the face region in the face image; the extraction module 202 is configured to input the face image into the attribute information extraction model; obtain the face attribute information of the face region And the environmental attribute information of the face image; according to the facial attribute information and the environmental attribute information, the face area is extracted to obtain the oily area in the face area; the oil removal module 203 is configured to be based on the facial attribute information and the environment. attribute information, and de-gloss processing is performed on the glossy area to obtain a de-glossy face image. For example, referring to FIG. 1, the acquisition module 201 can be used to execute S100-S101, the extraction module 202 can be used to execute S103, the degreasing module 203 can be used to execute S104, and the fusion module 205 can be used to execute S105.

In some embodiments, the obtaining module 201 is further configured to: obtain the first adjustment coefficient according to the facial attribute information and the environmental attribute information; the extracting module 202 is specifically configured to: increase each pixel in the face image according to the first adjustment coefficient The brightness value of ; determine the oily area in the face area according to the face area after increasing the brightness value.

In some embodiments, the acquiring module 201 is further configured to input the facial attribute information and the environmental attribute information into the adjustment coefficient extraction function to obtain the first adjustment coefficient; the adjustment coefficient extraction function is based on the adjustment marked in the multiple sample face images coefficients, facial attribute information and environmental attribute information obtained by linear regression analysis.

In some embodiments, the image processing apparatus 200 further includes an augmentation module 204 configured to: convert the color space of the face image into a target color space; the target color space includes information representing the brightness values of pixels in the face image ; Increase the brightness value of each pixel in the face image in the target color space according to the first adjustment coefficient.

In some embodiments, the extraction module 202 is further configured to: determine the area composed of pixels whose brightness value is greater than the first preset threshold in the face area after the brightness value has been increased as an oily area in the face area.

Optionally, the oily area in the face area satisfies the following formula:

M=pow(Y,s)

Among them, M is the oily area in the face area, pow is the exponential function; Y is the brightness value of each pixel in the face area after increasing the brightness value, s is the coefficient of the exponential function; and s is the facial attribute information. And the environmental attribute information is obtained by inputting the exponential coefficient calculation function; the exponential coefficient calculation function is obtained based on the exponential coefficient, facial attribute information and environmental attribute information of multiple sample face images marked by linear regression analysis.

In some embodiments, the degreasing module 203 is further configured to: input the facial attribute information and the environmental attribute information into a dimming coefficient calculation function to obtain a dimming coefficient of the face image; the dimming coefficient calculation function is based on a plurality of samples The dimming coefficient, facial attribute information and environmental attribute information marked in the face image are obtained by linear regression analysis; the brightness value of each pixel in the oily area is reduced according to the dimming coefficient of the face image.

In some embodiments, the image processing apparatus 200 further includes: a fusion module 205, which is configured to fuse the face image and the degreasing face image to obtain the target image.

In some embodiments, the extraction module 202 is further configured to: perform microdermabrasion processing on the face area; perform area extraction on the microdermabrasion processed face area according to the facial attribute information and the environmental attribute information, so as to obtain the human face area Oily areas in .

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here. In addition, for the explanation of any image processing apparatus 200 provided above and the description of the beneficial effects, reference may be made to the above-mentioned corresponding method embodiments, which will not be repeated.

Fig. 4 is a block diagram of an electronic device according to an exemplary embodiment. As shown in FIG. 4 , the electronic device 40 includes but is not limited to: a processor 401, a memory 402, a display 403, an input unit 404, an interface unit 405, a power supply 406, and the like.

The above-mentioned processor 401 is a memory for storing the above-mentioned processor-executable instructions. It can be understood that the above-mentioned processor 401 is configured to execute any step in the above-mentioned embodiment shown in FIG. 1 . That is, the block diagram of the electronic device 40 can be used as a hardware configuration diagram of the image processing apparatus 200 .

It should be noted that those skilled in the art can understand that the structure of the electronic device shown in FIG. 4 does not constitute a limitation on the electronic device, and the electronic device may include more or less components than those shown in FIG. some components, or a different arrangement of components.

The processor 401 is the control center of the electronic device, using various interfaces and lines to connect various parts of the entire electronic device, by running or executing the software programs and/or modules stored in the memory 402, and calling the data stored in the memory 402. , perform various functions of electronic equipment and process data, so as to monitor electronic equipment as a whole. The processor 401 may include one or more processing units; optionally, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem The modulation processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 401.

Memory 402 may be used to store software programs as well as various data. The memory 402 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required by at least one functional unit (such as an acquisition unit, a transceiving unit, or a merging unit, etc.). Additionally, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The display 403 is used to display information input by the user or information provided to the user. The display 403 may include a display panel, and the display panel may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.

The input unit 404 may include a Graphics Processing Unit (GPU), which processes image data of still pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frames can be displayed on display 403 . The image frames processed by the graphics processor may be stored in memory 402 (or other storage medium).

The interface unit 405 is an interface for connecting an external device to the electronic device 400 . For example, external devices may include wired or wireless headset ports, external power (or battery charger) ports, wired or wireless data ports, memory card ports, ports for connecting devices with identification modules, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. The interface unit 405 may be used to receive input (eg, data information, etc.) from an external device and transmit the received input to one or more elements within the electronic device 400 or may be used to communicate between the electronic device 400 and an external device transfer data.

The power supply 406 (such as a battery) can be used to supply power to various components. Optionally, the power supply 406 can be logically connected to the processor 401 through a power management system, so as to realize functions such as managing charging, discharging, and power consumption management through the power management system.

In an exemplary embodiment, an embodiment of the present disclosure further provides a storage medium including instructions, such as a memory 402 including instructions, and the above-mentioned instructions can be executed by the processor 401 of the electronic device 400 to complete the above-mentioned method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory) , RAM), CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices, etc.

In an example, referring to FIG. 3 , the receiving function of the above-mentioned acquisition module 201 may be implemented by the interface unit 405 in FIG. 4 . The processing functions of the acquisition module 201 , the extraction module 202 , the degreasing module 203 , the enlargement module 204 and the fusion module 205 can all be implemented by the processor 401 in FIG. 4 calling the computer program stored in the memory 402 .

In an exemplary embodiment, an embodiment of the present disclosure also provides a computer program product including one or more instructions, which can be executed by the processor 401 of the electronic device 400 to accomplish the above method.

It should be noted that when the instructions in the above-mentioned storage medium or one or more instructions in the computer program product are executed by the processor 401, each process of the above-mentioned method embodiment can be realized, and the same technical effect can be achieved. To avoid repetition, here No longer.

All the embodiments of the present disclosure can be implemented independently or in combination with other embodiments, which are all regarded as the protection scope required by the present disclosure.

Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or techniques in the technical field not disclosed by the present disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

An image processing method, comprising:

Obtain a face image, and determine the face area in the face image;

Inputting the face image into an attribute information extraction model to obtain the face attribute information of the face region and the environmental attribute information of the face image;

According to the facial attribute information and the environmental attribute information, region extraction is performed on the human face region to obtain a glossy region in the human face region;

According to the facial attribute information and the environmental attribute information, de-gloss processing is performed on the glossy area to obtain an image of the de-glossy face.
The method of claim 1, wherein,

The facial attribute information includes at least one of skin color, skin texture, brightness or age of the human face in the face region; the environmental attribute information includes at least ambient lighting information.
The method according to claim 1, wherein the performing region extraction on the face region according to the face attribute information and the environment attribute information to obtain a glossy region in the face region, comprising:

Obtain a first adjustment coefficient according to the facial attribute information and the environmental attribute information;

Increase the brightness value of each pixel in the face image according to the first adjustment coefficient;

According to the face area after the brightness value is increased, the oily area in the face area is determined.
The method according to claim 3, wherein the obtaining the first adjustment coefficient according to the face attribute information and the environment attribute information comprises:

Inputting the facial attribute information and the environmental attribute information into an adjustment coefficient extraction function to obtain the first adjustment coefficient; the adjustment coefficient extraction function is based on the adjustment coefficients and facial attribute information marked in the multiple sample face images And environmental attribute information obtained by linear regression analysis.
The method according to claim 3, wherein the increasing the brightness value of each pixel in the face image according to the first adjustment coefficient comprises:

Converting the color space of the face image into a target color space; the target color space includes information representing the brightness values of pixels in the face image;

The luminance value of each pixel in the face image in the target color space is increased according to the first adjustment coefficient.
The method according to claim 3, wherein the determining the oily area in the face area according to the face area after the increased brightness value comprises:

The area composed of pixels whose brightness value is greater than the first preset threshold in the face area after the brightness value has been increased is determined as the oily area in the face area.
The method according to claim 3, wherein, the oily area in the face area satisfies the following formula:

M=pow(Y,s)

Wherein, M is the oily area in the face area, and pow is an exponential function; Y is the brightness value of each pixel in the face area after increasing the brightness value, and s is the coefficient of the exponential function; And s is obtained by inputting the facial attribute information and the environmental attribute information into an exponential coefficient calculation function; the exponential coefficient calculation function is linear based on the exponential coefficient, facial attribute information and environmental attribute information marked on a plurality of sample face images. obtained by regression analysis.
The method according to any one of claims 1-7, wherein the performing de-gloss processing on the glossy area according to the facial attribute information and the environmental attribute information, comprising:

The facial attribute information and the environmental attribute information are input into the dimming coefficient calculation function to obtain the dimming coefficient of the face image; the dimming coefficient calculation function is based on the adjustment parameters marked in the multiple sample face images. Dark coefficient, facial attribute information and environmental attribute information obtained by linear regression analysis;

The brightness value of each pixel in the oily area is reduced according to the dimming coefficient of the face image.
The method according to any one of claims 1-7, further comprising:

The face image is fused with the degreasing face image to obtain a target image.
The method according to any one of claims 1-7, wherein the region extraction is performed on the face region according to the face attribute information and the environment attribute information, so as to obtain the Oily areas, including:

performing microdermabrasion on the face area;

According to the facial attribute information and the environmental attribute information, region extraction is performed on the face region after the skin resurfacing process, so as to obtain a shiny region in the face region.
An image processing device, comprising:

an acquisition module, configured to acquire a face image, and determine a face area in the face image;

an extraction module, configured to input the face image into an attribute information extraction model; obtain the face attribute information of the face region and the environment attribute information of the face image; according to the face attribute information and the environment attribute information, and region extraction is performed on the face region to obtain the glossy region in the face region;

The gloss removal module is configured to perform a gloss removal process on the glossy area according to the facial attribute information and the environmental attribute information, so as to obtain a glossy face image.
The apparatus of claim 11, wherein,

The facial attribute information includes at least one of skin color, skin texture, brightness or age of the human face in the face region; the environmental attribute information includes at least ambient lighting information.
The apparatus of claim 11, wherein,

The obtaining module is further configured to: obtain a first adjustment coefficient according to the face attribute information and the environment attribute information;

The extraction module is configured to: increase the brightness value of each pixel in the face image according to the first adjustment coefficient; determine the face region according to the face region after the increased brightness value Oily areas in .
The apparatus according to claim 13, wherein the acquisition module is configured to input the facial attribute information and the environmental attribute information into an adjustment coefficient extraction function to obtain the first adjustment coefficient; the adjustment coefficient extraction The function is obtained by linear regression analysis based on the adjustment coefficients, facial attribute information and environmental attribute information marked in multiple sample face images.
The apparatus of claim 13, wherein the image processing apparatus further comprises an enlargement module configured to:

Converting the color space of the face image into a target color space; the target color space includes information representing the brightness values of pixels in the face image;

The luminance value of each pixel in the face image in the target color space is increased according to the first adjustment coefficient.
The apparatus of claim 13, wherein the extraction module is configured to:

The area composed of pixels whose brightness value is greater than the first preset threshold in the face area after the brightness value has been increased is determined as the oily area in the face area.
The device according to claim 13, wherein the oily area in the face area satisfies the following formula:

M=pow(Y,s)

Wherein, M is the oily area in the face area, and pow is an exponential function; Y is the brightness value of each pixel in the face area after increasing the brightness value, and s is the coefficient of the exponential function; And s is obtained by inputting the facial attribute information and the environmental attribute information into an exponential coefficient calculation function; the exponential coefficient calculation function is linear based on the exponential coefficient, facial attribute information and environmental attribute information marked on a plurality of sample face images. obtained by regression analysis.
The apparatus of any one of claims 11-17, wherein the degreasing light module is configured to:

The facial attribute information and the environmental attribute information are input into the dimming coefficient calculation function to obtain the dimming coefficient of the face image; the dimming coefficient calculation function is based on the adjustment parameters marked in the multiple sample face images. Dark coefficient, facial attribute information and environmental attribute information obtained by linear regression analysis;

The brightness value of each pixel in the oily area is reduced according to the dimming coefficient of the face image.
The apparatus of any one of claims 11-17, further comprising:

The fusion module is configured to fuse the face image and the degreasing face image to obtain a target image.
The apparatus of any of claims 11-17, wherein the extraction module is configured to:

performing microdermabrasion on the face area;

According to the facial attribute information and the environmental attribute information, region extraction is performed on the face region after the skin resurfacing process, so as to obtain a shiny region in the face region.
An electronic device, comprising:

a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the executable instructions to implement the following processes:

Obtain a face image, and determine the face area in the face image;

The face image is input into the attribute information extraction model, to obtain the face attribute information of the face region and the environmental attribute information of the face image;

According to the facial attribute information and the environmental attribute information, region extraction is performed on the human face region to obtain a glossy region in the human face region;

According to the facial attribute information and the environmental attribute information, de-gloss processing is performed on the glossy area to obtain an image of the de-glossy face.
A computer-readable storage medium, characterized in that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the following processing:

Obtain a face image, and determine the face area in the face image;

Inputting the face image into an attribute information extraction model to obtain the face attribute information of the face region and the environmental attribute information of the face image;

According to the facial attribute information and the environmental attribute information, region extraction is performed on the human face region to obtain a glossy region in the human face region;

According to the facial attribute information and the environmental attribute information, de-gloss processing is performed on the glossy area to obtain an image of the de-glossy face.