WO2023005850A1

WO2023005850A1 - Image processing method and apparatus, and electronic device, storage medium and computer program product

Info

Publication number: WO2023005850A1
Application number: PCT/CN2022/107455
Authority: WO
Inventors: 苏柳
Original assignee: 上海商汤智能科技有限公司
Priority date: 2021-07-30
Filing date: 2022-07-22
Publication date: 2023-02-02
Also published as: CN113570581A

Abstract

The embodiments of the present disclosure relate to an image processing method and apparatus, and an electronic device, a storage medium and a computer program product. The method comprises: receiving a beautification operation for a target portion of a facial image; on the basis of a beautification color parameter of the target portion that is input in the beautification operation, generating a target color lookup table, which matches the beautification color parameter; and, according to an original color of a pixel point in the target portion of the facial image and the target color lookup table, generating a beautified facial image.

Description

Image processing method and device, electronic device, storage medium and computer program product

Cross References to Related Applications

This disclosure is based on the Chinese patent application with the application number 202110872286.2, the application date is July 30, 2021, and the application name is "Image processing method and device, electronic equipment and storage medium", and claims the priority of the Chinese patent application, The entire content of this Chinese patent application is hereby incorporated by reference into this disclosure.

technical field

The present disclosure relates to the field of computer vision, and in particular to an image processing method and device, electronic equipment, storage media and computer program products.

Background technique

Lip makeup refers to the beauty makeup of the lips. The lips after lip makeup modification are generally pure and shiny. With the development of computer vision technology, processing images containing lips to obtain images processed by lip makeup has become more and more widely used in people's daily life. However, along with the development of lip makeup, users are not satisfied with only obtaining the processed image of lip makeup based on several colors provided.

Contents of the invention

Embodiments of the present disclosure provide an image processing method and device, electronic equipment, a storage medium, and a computer program product.

According to an aspect of the embodiments of the present disclosure, there is provided an image processing method, including: receiving a beautification operation on a target part of a human face image; based on the beautification color parameters of the target part input in the beautification operation, generating and A target color lookup table for matching the beautification color parameters; generating a beautified face image according to the original color of pixels in the target part of the face image and the target color lookup table.

According to an aspect of an embodiment of the present disclosure, an image processing device is provided, including: a receiving module configured to receive a beautification operation on a target part of a human face image; a generating module configured to based on the beautification operation input The beautification color parameter of the target part generates a target color lookup table matching the beautification color parameter; the beautification module is configured to look up the target color according to the original color of the pixel in the target part of the face image, Generate beautified face images.

According to an aspect of an embodiment of the present disclosure, there is provided an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to: execute the above image processing method.

According to an aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which computer program instructions are stored, and the above-mentioned image processing method is implemented when the computer program instructions are executed by a processor.

According to an aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer-readable storage medium storing program codes, and when instructions included in the program codes are executed by a processor of a computer device, the above-mentioned image processing method is implemented. .

In the embodiment of the present disclosure, by receiving the beautification operation on the target part of the face image, and based on the beautification color parameters input in the beautification operation, a color lookup table corresponding to the beautification color parameter matching is generated, so that according to the target part of the face image The original color of the pixel and the target color lookup table to generate a beautified face image. Through the above process, the corresponding target color lookup table can be generated according to any input beautification color parameters in the beautification operation, so as to realize the beautification of the color of the target part. On the one hand, the color of the beautification operation can be enriched by any input beautification color parameters. Improve the freedom of beautification operation; on the other hand, the beautified face image can have a more natural beautification effect through the target color lookup table.

It should be understood that the above general description and the following detailed description are exemplary and explanatory, rather than limiting the present disclosure. According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features of the embodiments of the present disclosure and aspects will become clear.

Description of drawings

The accompanying drawings here are incorporated into the description and constitute a part of the present description. These drawings show embodiments consistent with the present disclosure, and are used together with the description to explain the technical solution of the present disclosure.

FIG. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

FIG. 2A shows a schematic diagram of an input interface of a beautification operation according to an embodiment of the present disclosure;

FIG. 2B shows a flowchart of an image processing method according to an embodiment of the present disclosure;

FIG. 3 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

Fig. 4 shows a schematic diagram of a preset color lookup table according to an embodiment of the present disclosure;

FIG. 5A shows a flowchart of an image processing method according to an embodiment of the present disclosure;

FIG. 5B shows a flowchart of an image processing method according to an embodiment of the present disclosure;

FIG. 6 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

Fig. 7 shows a schematic diagram of raw materials according to an embodiment of the present disclosure;

Fig. 8 shows a schematic diagram of a face image according to an embodiment of the present disclosure;

Fig. 9 shows a schematic diagram of a beautified human face image according to an embodiment of the present disclosure;

Fig. 10 shows a block diagram of an image processing device according to an embodiment of the present disclosure;

Fig. 11 shows a flowchart of an image processing method according to an application example of the present disclosure;

Fig. 12 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the term "at least one" herein means any one of a variety or any combination of at least two of the more, for example, including at least one of A, B, and C, which may mean including from A, Any one or more elements selected from the set formed by B and C.

In addition, in order to better illustrate the present disclosure, numerous details are given in the following specific embodiments. It will be understood by those skilled in the art that the present disclosure may be practiced without certain of the details. In some instances, methods, means, components and circuits that are well known to those skilled in the art have not been described in detail so as to obscure the gist of the present disclosure.

FIG. 1 shows a flow chart of an image processing method according to an embodiment of the present disclosure. The method can be applied to an image processing device or an image processing system, and the image processing device can be a terminal device, a server, or other processing devices. Wherein, the terminal device may be user equipment (User Equipment, UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (Personal Digital Assistant, PDA), handheld device, computing device, vehicle-mounted device, Wearable equipment etc. In an example, the image processing method can also be applied to a cloud server or a local server. The cloud server can be a public cloud server or a private cloud server, which can be flexibly selected according to actual conditions.

In some possible implementation manners, the image processing method may be implemented by a processor invoking computer-readable instructions stored in a memory.

As shown in Figure 1, in a possible implementation, the image processing method is executed by an electronic device, the electronic device may be the above-mentioned image processing device or a cloud server, or a local server, and the method may include:

Step S11, receiving a beautification operation on the target part of the face image.

Wherein, the face image can be any image containing a face, and the face image can contain one face, or multiple faces, and its implementation form can be flexibly determined according to the actual situation, and is not limited in the embodiments of the present disclosure. .

The beautification operation can be any operation that performs beautification processing on the target part of the face image, such as lip makeup operation, eye makeup operation, facial repair operation, or hairdressing operation. The operation content included in the beautification operation can be flexibly determined according to the actual situation, and is not limited to the following disclosed embodiments. In a possible implementation manner, the beautification operation may include an operation indicating to perform beautification processing on the face image; in some possible implementation manners, the beautification operation may also include inputting at least one parameter, such as processing type, Beautify color parameters or adjust parameters, etc.

The processing type may be the type performed in the beautification operation. With the different forms of the beautification operation, the processing type included in the beautification operation may also be flexibly changed, and the beautification operation may include at least one processing type. In a possible implementation manner, when the beautification operation includes a lip makeup operation, the treatment type may include at least one of natural treatment, metallic light effect, matte light effect, moist light effect, and shimmering light effect. Among them, the natural treatment can include the natural modification of the lip color, retaining the original glossy effect of the lips; the treatment types such as metallic light effect, matte light effect, moist light effect and shimmering light effect can realize the modification of lip color and the glossy effect. Effects can be changed to obtain lip makeup effects with metallic luster, matte lip makeup effects with low gloss, moisturizing lip makeup effects with high gloss and natural brightness transition, and high brightness, high gloss and brightness. Interval flashing lip makeup effects, etc.

The beautification color parameter can be any parameter input in the beautification operation to beautify the color of the target part of the face image. The form of the beautification color parameter can be flexibly determined according to the actual situation. In a possible implementation, the beautification The color parameter can be an input RGB color parameter.

The adjustment parameters can be input during the beautification operation, and are related parameters for beautifying and adjusting the target part of the face image. The adjustment parameters can include various parameter types. In some possible implementations, the adjustment parameters can include at least one of the following : Beautification strength, brightness strength, etc. of the color of the target part of the face image. Based on the adjustment parameters, the way of beautifying and adjusting the target part of the face image can be referred to the following disclosed embodiments in detail, and will not be expanded here.

Fig. 2A shows a schematic diagram of an input interface of a beautification operation according to an embodiment of the present disclosure. As shown in Fig. 2A, in an example, you can select lip makeup operation, blush operation, eye shadow operation, eyeliner operation, and eyelash operation on the input interface. Various types of beautification operations such as brush operation, eyebrow operation, foundation operation or hair dyeing operation, and select the processing type of beautification operation in the input interface, as shown in Figure 2A, select the matte light effect processing type in the beautification operation, and Beautification color parameters can be input in the input interface, such as the color values of the three RGB color channels shown in Figure 2A, and other adjustment parameters can also be input, such as the highlights (L, HighLight) and middle Tune (M, Midtones), etc.

Based on FIG. 2A, it can also be seen that in an example, the input interface can also display a face image (in order to protect the objects in the figure, mosaic processing is performed on some parts of the face), and the face image can be obtained through the camera. The currently collected image obtained by collecting may also be a selected photo. In an example, the face image and the beautified face image may be displayed in split screens on the input interface.

The target part can be any part of the face image that needs to be beautified. Which parts are included in the target part, the implementation form can also be flexibly determined according to the actual situation of the beautification operation. In one possible implementation, the beauty operation includes lip In the case of a makeup operation, the target site may include a lip site.

Step S12, based on the beautification color parameters of the target part input in the beautification operation, a target color lookup table matching the beautification color parameters is generated.

For the implementation form of the beautification color parameters, reference may be made to the above disclosed embodiments. In a possible implementation, when the beautification color parameters include RGB color parameters, three beautification colors in red (R, Red), green (G, Green) and blue (B, Blue) can be input respectively. The value of the color parameter on the color channel, so as to obtain the input beautification color parameter.

The target color lookup table may include target output color parameters, and the correspondence between target output color parameters and input colors, where the input color may be a color that is searched from the target color lookup table, and the target output color parameters may contain multiple target The output color, the target output color may be the output color corresponding to the input color found in the target color lookup table. For example, if the input color A is searched in the target color lookup table, the target output color B corresponding to A can be found in the target color lookup table. The corresponding relationship between colors in the target color lookup table can be flexibly set according to the actual situation, which is not limited in this embodiment of the present disclosure. In a possible implementation manner, the multiple target output colors in the target color lookup table may be arranged in a gradient manner, and the arrangement manner is not limited in the embodiments of the present disclosure, and is not limited to the following disclosed embodiments.

In a possible implementation, a target color lookup table matching the beautification color parameters can be generated according to the beautification color parameters input in the beautification operation. In this case, the target output color parameters in the target color lookup table belong to Within the range of the beautification color parameters, so that the target output color parameters found according to the target color lookup table all match the beautification color parameters, thereby achieving the purpose of beautifying the target part of the face image according to the beautification color parameters.

How to generate the target color lookup table based on the beautification color parameters can be flexibly determined according to the actual situation. For example, the color in the original preset color lookup table can be corrected according to the beautification color parameters to obtain the target color lookup table; Or directly select the target color lookup table bound to the beautification color parameters according to the beautification color parameters; or generate the target color lookup table according to certain color mapping rules according to the beautification color parameters. For some possible implementation manners of step S12, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

Step S13, generating a beautified face image according to the original color of the pixels in the target part of the face image and the target color lookup table.

Wherein, the original color may be the unprocessed color of the target part in the face image. In some possible implementations, the original color of each pixel in the target part may be determined according to the position of the target part in the face image .

The face image after beautification can be the face image obtained by beautifying the original color according to the target color lookup table. The method of generating the face image after beautification can be flexibly determined according to the actual situation. The original color of the pixel is searched for the corresponding target output color parameter in the target color lookup table as the color of each pixel in the beautified face image; or the corresponding target can be found in the target color lookup table according to the original color After the color parameters are output, the target output color parameters are fused with the original color to serve as the color of each pixel in the beautified face image. For some possible implementation manners of step S13, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

In a possible implementation, as shown in FIG. 2B, step S11 may include:

Step S111 , acquiring a face image in response to a face image confirmation operation.

Step S112, in response to the beautification operation, receiving at least one of the processing type, beautification color parameters and adjustment parameters input in the beautification operation.

Wherein, the face image confirmation operation may be used to confirm the face image to be beautified. The form of the face image confirmation operation can be flexibly determined according to the actual situation, and is not limited to the following disclosed embodiments. In a possible implementation manner, the face image confirmation operation may include: transmitting the face image, or selecting a face image from a preset image library.

Wherein, the face image transmission may be that the user actively uploads the face image, and in response to the face image confirmation operation of the face image transmission, the face image uploaded by the user may be obtained by receiving.

The preset image library can include a plurality of preset face images, and the user can select one or more preset face images from the preset image library as the face image to be beautified. Therefore, in a In a possible implementation manner, in response to the face image confirmation operation of selecting a face image in the preset image library, the selected face image may be read from the preset image library by means of reading.

The implementation of the beautification operation can refer to the above-mentioned disclosed embodiments. As described in the above-mentioned various disclosed embodiments, the beautification operation can include outputting at least one parameter, so correspondingly, in response to the beautification operation, the processing type input in the beautification operation can be received , at least one of a beautification color parameter and an adjustment parameter.

In the embodiments of the present disclosure, the execution order of the face image confirmation operation and the beautification operation can be flexibly selected according to the actual situation. Class parameters, and then perform face image confirmation operation, or perform face image confirmation operation and beautification operation at the same time, so correspondingly, the input processing type, beautification color parameters and adjustment parameters in the acquisition of face image and reception beautification operation The execution sequence of at least one of the processes can be flexibly selected according to the actual situation, which is not limited in this embodiment of the present disclosure.

Through the embodiments of the present disclosure, according to the actual situation, the face image to be beautified can be flexibly obtained by receiving or reading, and various parameters of the beautification operation can be flexibly obtained according to the parameters input by the user, which greatly improves the overall The flexibility and interactivity of the image processing method improve the user's operation experience for beautification.

FIG. 3 shows a flow chart of an image processing method according to an embodiment of the present disclosure. As shown in FIG. 3 , in a possible implementation manner, step S12 may include:

Step S121, obtaining a preset color lookup table and preset color parameters corresponding to the preset color lookup table;

Step S122, determining the color deviation between the beautification color parameters and the preset color parameters;

Step S123, based on the color deviation, adjust the first output color parameter of the preset color lookup table to obtain a target color lookup table.

Wherein, the preset color lookup table may be any preset color lookup table. Similar to the target color lookup table, the preset color lookup table may include a first output color parameter, and a correspondence between the first output color parameter and an input color, wherein the first output color parameter may include multiple first output colors, The first output color may be the output color found in the preset color lookup table according to the input color. The multiple first output colors in the preset color lookup table can also be arranged in a gradient form, and the implementation form can refer to the target color lookup table.

Fig. 4 shows a schematic diagram of a preset color lookup table according to an embodiment of the present disclosure. It can be seen from the figure that in one example, the preset color lookup table includes a plurality of gradient colors with natural transitions as the first output color (Due to the limitations of the grayscale image display, the colors with different shades in the image are actually gradient colors with color differences). Based on the input color, a first output color corresponding to the input color can be found from a preset color lookup table.

The preset color parameter may be a color parameter matched with the preset color lookup table, and the color of the preset color parameter may be determined according to the actual situation of the preset color lookup table, which is not limited in this embodiment of the present disclosure. The form of the preset color parameter can refer to the beautification color parameter, for example, it can also be a color parameter in the form of RGB. Since the preset color parameters match the preset color lookup table, in some possible implementations, the preset color lookup table can be directly used as the target when the beautification color parameters input in the beautification operation are the same as the preset color parameters Color lookup table.

In some possible implementations, the beautification color parameters input in the beautification operation may be different from the preset color parameters. In this case, the preset color can be adjusted according to the color deviation between the beautification color parameters and the preset color parameters. The multiple first output colors in the lookup table are adjusted, so as to obtain a target color lookup table matching the beautification color parameters.

Wherein, the color deviation between the beautification color parameter and the preset color parameter can be the color difference between the beautification color parameter and the preset color parameter. With the difference between the beautification color parameter and the preset color parameter, the color deviation The form of is also different. In some possible implementations, when both the beautification color parameters and the preset color parameters are RGB parameters, the color deviation can also be in the form of RGB; in some possible implementations, the beautification color parameters are the same as The form of preset color parameters may be different. For example, the beautification color parameter may be an RGB parameter, while the preset color parameter may be a parameter in the form of HSV (hue H, saturation S, and lightness V). In this case, the beautification color parameter may be The color parameters and preset color parameters are unified into the same color space, and then the color deviation is calculated. The color space to be unified can be flexibly determined according to the actual situation, and is not limited in the embodiments of the present disclosure.

The method of adjusting the first output color parameter in the preset color lookup table based on the color deviation is not limited in this embodiment of the disclosure. In some possible implementations, the first output color parameter can be directly The multiple first output colors of are added to the color deviation to obtain the target output color parameter. In some possible implementations, after adding the multiple first output colors to the color deviation respectively, according to the preset color parameter The range adjusts the result of the addition to obtain the target output color parameters, etc. For some possible implementations of step S123, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

Through the embodiments of the present disclosure, the color deviation between the input beautification color parameters and the preset color parameters can be used to adjust the preset color lookup table to obtain the corresponding target color lookup table, reducing the cost of generating the target color lookup table The amount of data that needs to be processed in the process reduces the difficulty of generating the target color lookup table, and improves the convenience, feasibility and efficiency of image processing. While improving the convenience of image processing, it reduces the pressure on hardware storage, so as to achieve the purpose of saving costs.

FIG. 5A shows a flowchart of an image processing method according to an embodiment of the present disclosure. As shown in FIG. 5A, in a possible implementation, step S123 may include:

Step S1231, converting the first output color parameter in the preset color lookup table to the preset color space to obtain the second output color parameter;

Step S1232, in the preset color space, adjust the second output color parameter according to at least one of color deviation and beautification color parameters, to obtain a third output color parameter;

Step S1233, generating a target color lookup table according to the third output color parameter.

Wherein, the preset color space can be any color space form such as RGB color space, HSV color space or HSL (hue H, saturation S and lightness L), which color space to choose can be flexibly set according to the actual situation. In a possible implementation manner, in order to uniformly implement adjustments to the multiple first output colors in the preset color lookup table, the HSV color space may be used as the preset color space.

The second output color parameter may be a color parameter obtained by converting the first output color parameter into a preset color space. As described in the above disclosed embodiments, the first output color parameter may include a plurality of first output colors, correspondingly , the second output color parameter may include a plurality of second output colors, and each second output color may be obtained by respectively converting the first output color into a preset color space.

The implementation of step S1231 can be flexibly determined according to the form of the first output color parameter and the form of the preset color space. In one example, the first output color parameter can include multiple first output colors in the form of RGB, and the preset color The space may be an HSV color space. In this case, according to the color mapping relationship between RGB and HSV, the first output colors in the form of a plurality of RGB in the first output color parameter may be respectively converted into a range of [0.0 , 1.0] of the second output color in HSV form to obtain the second output color parameter.

The color deviation may include the color deviation between the beautification color parameters and the preset color parameters in the preset color space. As described in the above disclosed embodiments, the preset color space may include the HSV color space. In this case, the beautification can be respectively The color parameters and the preset color parameters are converted into the HSV space to obtain the color deviation in the HSV space. In one example, the process of obtaining the color deviation can be expressed by the following formula (1):

diff=target_hsv-lip_ref_hsv (1)

Among them, diff is the color deviation in the HSV color space, target_hsv is the beautification color parameter converted to the HSV color space, and lip_ref_hsv is the preset color parameter converted to the HSV color space.

In step S1232, the third output color parameter may also include a plurality of third output colors, and each third output color may be a color obtained by adjusting the second output color respectively. Since both the second output color and the color deviation belong to the preset color space, the plurality of second output colors can be respectively adjusted according to the color deviation in the preset color space to obtain a plurality of third output colors.

In some possible implementations, the second output color can also be adjusted directly according to the beautification color parameter to obtain the third output color. In this case, the beautification color parameter used to adjust the second output color is also Can belong to a preset color space. For some possible implementations of step S1232, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

In step S1233, the method of generating the target color lookup table according to the third output color parameter can also be flexibly determined according to the actual situation, for example, multiple third output colors in the third output color parameter can be directly used as the target color lookup table Output color, or according to the preset range of the target output color parameter, adjust part or all of the colors in the third output color to obtain the target output color parameter, etc., see the following disclosed embodiments for details, and do not mention it here Do unfold.

Through the embodiments of the present disclosure, in the preset color space, the first output color parameter can be adjusted by using the color deviation to generate the target color lookup table, so that by selecting an appropriate preset color space, it is convenient to adjust the output color in the preset color space The first output color parameters are adjusted in batches to improve the generation efficiency and editing degree of the target color lookup table, thereby improving the efficiency and convenience of image processing.

In a possible implementation manner, step S1232 may include at least one of the following operations:

According to the hue component of the beautification color parameter, the hue component of the second output color parameter is adjusted to obtain the hue component of the third output color parameter.

According to the saturation component of the color deviation, the hue component of the second output color parameter is adjusted to obtain the saturation component of the third output color parameter.

According to the brightness component of the color deviation, the brightness component of the second output color parameter is adjusted to obtain the brightness component of the third output color parameter.

As described in the above disclosed embodiments, the preset color space may include the HSV color space, and correspondingly, the HSV color space may include color parameter components, which are respectively: hue component (H, Hue), saturation component (S, Saturation ) and the brightness component (V, Value).

Based on different color parameter components in the HSV color space, the manner of adjusting the second output color parameter can also be changed flexibly.

In a possible implementation, the H component of the second output color parameter can be adjusted according to the hue component H of the color deviation in the HSV color space to obtain the H component of the third output color parameter. For example, in In an example, the H component of the color deviation may be added to the H components of multiple second output colors in the second output color parameter to obtain the H components of multiple third output colors in the third output color parameter.

In a possible implementation, considering that the H component is an angle measure, and the value range is between 0 degrees (°) and 360°, it can also be directly based on the H component in the HSV color space of the beautification color parameter, to adjust the H component of the second output color parameter to obtain the H component of the third output color parameter. For the adjustment method, please refer to the above-mentioned adjustment method based on color deviation.

Similarly, in a possible implementation, the S component and the V component of the second output color parameter can be adjusted respectively according to the saturation component S and the lightness component V of the color deviation in the HSV color space to obtain the first The S component and V component of the three output color parameters.

Through the embodiments of the present disclosure, in the preset color space, the different color components of the second output color parameters can be adaptively adjusted based on at least one of the color deviation and beautification color parameters, respectively, to obtain the third output color Different component values in the preset color space effectively improve the flexibility of obtaining the third output color parameter, thereby improving the flexibility of image processing.

In a possible implementation manner, as shown in FIG. 5B, step S1233 may include:

Step S1233a, if the third output color parameter belongs to the preset range, use the third output color parameter as the target output color parameter in the target color lookup table.

Step S1233b, if the third output color parameter exceeds the preset range, determine the target output color parameter in the target color lookup table based on the critical color parameter in the preset range.

Wherein, the range value of the preset range can be flexibly determined according to the actual situation. For example, in a possible implementation manner, the third output color parameter can be a color parameter transformed in the HSV color space. Since the HSV color space In , the range of the H component is between 0° and 360°, and the ranges of the S and V components are both between [0.0, 1.0]. Therefore, according to the ranges of the H, S and V components, the first The three output color parameters are adjusted to obtain the target output color parameters.

In a possible implementation, when the H component of the third output color parameter is between 0° and 360°, the H component of the third output color parameter can be directly used as the H component of the target output color parameter , when the H component of the third output color parameter exceeds the range between 0° and 360°, the remainder may be calculated for the H component of the third output color parameter based on the critical color parameter 360° of the preset range of the H component, And the obtained remainder is used as the H component of the target output color parameter. In an example, the process can be expressed by the following formula (2) or (3):

table2_hsv.h＝fract(table1_hsv.h+target_hsv.h) (2)

table2_hsv.h＝fract(table1_hsv.h+diff.h) (3)

Among them, table2_hsv.h is the H component of the target output color parameter, table1_hsv.h is the H component of the second output color parameter, target_hsv.h is the H component of the beautification color parameter converted to HSV color space, and diff.h is the color deviation The H component of , fract(·) means to find a decimal.

In a possible implementation, when the S component of the third output color parameter is between [0.0, 1.0], the S component of the third output color parameter can be directly used as the S component of the target output color parameter , when the S component of the third output color parameter exceeds [0.0, 1.0], the critical color parameter 0.0 or 1.0 in the preset range of the S component can be used as the S component of the target output color parameter to determine the target The process of outputting the V component of the color parameter can refer to the determination process of the S component. In an example, the process of determining the target output color parameters S component and V component can be expressed by the following formulas (4) and (5):

table2_hsv.s＝clamp(table1_hsv.s+diff_hsv.s,0.0,1.0) (4)

table2_hsv.v＝clamp(table1_hsv.v+diff_hsv.v,0.0,1.0) (5)

Among them, table2_hsv.s is the S component of the target output color parameter, table1_hsv.s is the S component of the second output color parameter, diff.s is the S component of the color deviation, table2_hsv.v is the V component of the target output color parameter, table1_hsv .v is the V component of the second output color parameter, diff.v is the V component of the color deviation, clamp(a,min,max) is an interval limiting function, which is used to limit a between the range of min and max, When a exceeds the range defined by min and max, the value of min or max will be returned.

In some possible implementations, the target output color parameter can also be converted back to the same color space as the first output color parameter according to the form of the first output color parameter in the preset color lookup table, for example, in a In an example, the first output color parameters in the preset color lookup table may all be in RGB format. In this case, the obtained target output color parameters in HSV format may be converted back to RGB format to obtain the target color lookup table.

Through the embodiments of the present disclosure, the third output color can be further adjusted according to the preset range, and the target output color parameters belonging to the preset range can be obtained, and then the target color lookup table can be obtained. Through the above process, a more accurate target color lookup can be obtained The table ensures that the beautified face image can be generated, reduces the occurrence of color pixels out of range in the beautified face image, and improves the accuracy and effect of image processing.

FIG. 6 shows a flowchart of an image processing method according to an embodiment of the present disclosure. As shown in FIG. 6, in a possible implementation manner, step S13 may include:

Step S131, in the target color lookup table, look up the target output color parameter corresponding to the original color of the pixel in the target part as the initial target color of the pixel in the target part.

Step S132: Determine the target color of the pixels in the target part according to the initial target color of the pixels in the target part.

Step S133, based on the original color of the pixels in the target part and the target color, determine the beautified human face image.

Wherein, the initial target color may be the target output color parameter found by searching the corresponding color in the target color lookup table by taking the original color of the pixel point in the target part as the input color.

For the implementation form of the original color of the pixels in the target part, reference may be made to the above disclosed embodiments. The manner of obtaining the original color of the pixel in the target part of the face image can be flexibly determined according to the actual situation, and is not limited to the following disclosed embodiments.

In a possible implementation, the original material can be placed at the position of the target part in the standard face image to obtain a standard material image, wherein the original material can be determined according to the target part of the beautification operation, as shown in Figure 7 A schematic diagram of an original material according to an embodiment of the present disclosure is shown, as shown in FIG. 7 , in an example, when the beautification operation is a lip makeup operation, the original material may be a lip mask (mask). And in the face image, determine the key points of the face through key point recognition, use the key points of the face and interpolate the interpolation points through the key points of the face, and construct the triangular mesh of the target area in the face image. According to the constructed triangular mesh, the position of the target part in the face image can be determined, and based on the position, the standard material image can be sampled to obtain the target material. Based on the obtained target material, when the transparency of the pixel in the target material belongs to the preset transparency range, the area corresponding to the position of the pixel in the face image can be used as the image area where the target part is located, and the pixel can be extracted. The original color of multiple pixels in the image area.

Wherein, the range of the preset transparency range can be flexibly determined according to the actual situation. In a possible implementation, the preset transparency range can be set to be lower than 100%, that is, the transparency of pixels in the target material is lower than In the case of 100% (not fully transparent), the area corresponding to the position of the pixel in the face image can be used as the image area where the target part is located, and the original color of the pixel in the image area is extracted; in a possible implementation In the manner, the preset transparency range may also be set to be lower than other transparency values, or within a certain transparency range, etc. The embodiment of the present disclosure does not limit the range value of the preset transparency range.

By extracting the original color of the pixel point corresponding to the face image when the transparency of the pixel point in the target material belongs to the preset transparency range, through the above process, the value of the preset transparency range can be set, and more Specifically determine the image area where the target part that meets the requirements is located, so as to extract more accurate original colors in the target part from the face image, and then improve the reliability and authenticity of the subsequent fused face image.

According to the initial target color, the target color of the pixels in the target part can be determined. In some possible implementations, the initial target color can be directly used as the target color. In some possible implementations, it can also be based on the output of the beautification operation. Processing type, adjust the initial target color accordingly, such as brightness adjustment, etc., to obtain the target color. For some possible implementation manners of step S132, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

Based on the original color and the target color of the pixels in the target part, the beautified human face image can be obtained through step S133. The implementation of step S133 can be flexibly determined according to the actual situation. In some possible implementations, the original color of the pixel in the target part can be fused with the target color, and the fused color can be used as the pixel in the beautified face image. The color of the point; in some possible implementations, it is also possible to determine the fusion ratio of the original color and the target color according to the adjustment parameters input in the beautification operation, such as the intensity of the adjustment parameters, and then compare the original color and the target color according to the fusion ratio The colors are fused to obtain a beautified face image and the like.

Through the embodiments of the present disclosure, the initial target color can be determined based on the target color lookup table, and other parameters input in the beautification operation can be used to adjust the initial target color to determine the color of the pixels in the beautified face image, and obtain a more Beautified face images that are natural and meet user needs, and improve the interaction level and user experience of image processing.

In a possible implementation manner, step S132 may include:

When the processing type in the beautification operation includes natural processing, the initial target color of the pixels in the target part is used as the target color of the pixels in the target part. or,

When the processing type in the beautification operation includes metal light effect processing, the initial target color of the pixel in the target part is adjusted based on the randomly obtained noise value to obtain the target color of the pixel in the target part.

Wherein, the treatment effects of the natural treatment and the metal light effect treatment can refer to the above disclosed embodiments. The noise value can be the noise value or information added to each pixel in the image. The method of randomly obtaining the noise value can be to obtain the randomly obtained noise value by generating random data. The method of generating random data is implemented in this disclosure. The examples are not limited, see the following disclosed examples for details, and will not be expanded here.

In a possible implementation manner, when the processing type is natural processing, the initial target color may be directly used as the target color.

In a possible implementation, when the processing type is metal light effect processing, the initial target color of at least one pixel in the target part can be adjusted based on randomly obtained noise values, so as to change the color of different pixels. The color makes the target area appear metallic light effect effect. Among them, the color of which pixels are adjusted, and how to adjust the initial target color based on the randomly obtained noise value, the implementation method can be flexibly changed according to actual needs, and is not limited to the following disclosed embodiments.

In one example, the texture coordinates can be used to sample the preset noise texture to obtain the random noise value corresponding to each pixel in the lip image; for each pixel, it is judged whether the corresponding noise value is within the preset Set within the noise range (the preset noise range can be distributed in different parts between 0 and 1, such as 0.98 to 1.0, 0.78 to 0.8, etc.); if it is within the preset noise range, use the following method to determine the pixel point The adjustment coefficient of the pixel, otherwise the following method 2 is used to determine the adjustment coefficient of the pixel:

Method 1. Calculate the adjustment factor through the noise value and the transparency of the target material:

The adjustment factor is first equal to the noise value;

Adjustment coefficient = adjustment coefficient * pow (transparency of target material, 4.0).

Among them, pow(x, y) indicates the result of calculating the yth power of x, so pow(transparency, 4.0) is the value of calculating the 4th power of the transparency.

Method 2. Calculate the adjustment coefficient by calculating the first brightness of the pixel (the brightness value corresponding to the color value of the pixel), the second brightness, the third brightness, and the preset brightness radius (determining the radius of the highlight point):

If the first brightness is less than the third brightness, then:

Adjustment coefficient=(third brightness-first brightness)/(1.0-first brightness);

If the first brightness is greater than the third brightness, then:

Adjustment coefficient=pow((first brightness-third brightness)/(second brightness-third brightness), shinness), where shinness is a preset brightness radius.

After the adjustment coefficient is determined by method 1 or method 2, the initial target color can be adjusted according to the obtained adjustment coefficient and the preset light source value to obtain the target color:

Target color = initial target color + adjustment factor × light source value.

Wherein, the first brightness may be a brightness value determined according to the color value of the original color of the pixel, where the brightness value may be determined by calculating the color value, and in one example, the brightness value may be determined according to three of the color values The values of the color channels (Red R, Green G, and Blue B) are calculated.

The second brightness may be determined according to the color value of the pixel with the target brightness, wherein the pixel with the target brightness may be located within the preset processing range of the pixel in the target part of the face image and has the highest brightness of pixels. Wherein, the size of the preset processing range can be flexibly set according to actual conditions, and is not limited in this embodiment of the present disclosure.

The third brightness may be a brightness value determined according to a color value of an intermediate color of a pixel, wherein the intermediate color of a pixel may be a color obtained by filtering the pixel through a preset convolution kernel. Wherein, the form and size of the preset convolution kernel can be flexibly set according to the actual situation. In a possible implementation, the filtering range of the preset convolution kernel is consistent with the preset processing range in the above disclosed embodiments, namely In an example, on the one hand, the pixel can be filtered through the preset convolution kernel to obtain the intermediate color of the pixel after filtering, and the corresponding brightness value can be calculated according to the color value of the intermediate color as the third brightness; On the one hand, the area covered by the preset convolution kernel to filter the pixels can be used as the preset processing range, then in the target part of the face image, the brightness value of the pixel that is within the preset processing range and has the highest brightness , can be used as the second brightness.

The preset light source value may be determined according to the brightness intensity in the adjustment parameters input during the beautification operation.

In some possible implementations, the processing type may also include matte light effects, wet light effects, or flickering light effects, etc. In these cases, the first brightness and second brightness mentioned in the above disclosed embodiments may be used and the third brightness to adaptively adjust the initial target color to obtain the target color matching the processing type, etc. The processing manner can be flexibly determined according to the actual situation, and is not limited in this embodiment of the present disclosure.

Through the embodiments of the present disclosure, when the processing types corresponding to the beautification operation are different, different methods can be selected to adjust the initial target color to determine the target color, which improves the flexibility of the beautification operation; and through the randomly obtained noise value, To adjust the initial target color of at least one pixel in the target part, the color can be adjusted based on random data to obtain a more natural metallic light effect.

Based on the above disclosed embodiments, it is possible to obtain a beautified human face image obtained by performing a beautification operation on the human face image. Fig. 8 shows a schematic diagram of a human face image. After the beautification operation is performed on the human face image in Fig. 8, a schematic diagram of the beautified human face image in Fig. 9 is obtained (in order to protect the objects in the image, each figure Mosaic processing has been carried out on some parts of the human face), as can be seen by comparison, according to the image processing methods proposed in the above-mentioned various disclosed embodiments, a more real and natural human face image after beautification with a better beautifying effect on the lips can be obtained .

In some possible implementation manners, the methods proposed in the embodiments of the present disclosure may further include:

In response to the preview operation, the beautified face image is displayed.

Wherein, the preview operation may be selected by the user, and needs to perform a real-time preview operation on the beautified face image. In response to the preview operation, the beautified face image may be displayed on the human-computer interaction interface for the user to view.

In some possible implementation manners, the generated beautified face image may also be actively displayed in real time.

Through the embodiments of the present disclosure, the beautified human face image can be displayed in real time in response to the preview operation, so as to improve the degree of interaction with the user and enhance the user experience.

FIG. 10 shows a block diagram of an image processing device according to an embodiment of the present disclosure. As shown in Figure 10, the image processing device 20 may include:

The receiving module 21 is configured to receive the beautification operation on the target part of the face image.

The generation module 22 is configured to generate a target color lookup table matching the beautification color parameters based on the beautification color parameters of the target part input in the beautification operation.

The beautification module 23 is configured to generate a beautified human face image according to the original color of the pixels in the target part of the human face image and the target color lookup table.

In a possible implementation manner, the generating module is configured to: acquire a preset color lookup table and preset color parameters corresponding to the preset color lookup table; determine the color deviation between the beautification color parameters and the preset color parameters; Based on the color deviation, the first output color parameter of the preset color lookup table is adjusted to obtain a target color lookup table.

In a possible implementation manner, the color deviation includes the color deviation between the beautification color parameter and the preset color parameter in the preset color space; the generation module is configured to: convert the first output color parameter in the preset color lookup table to Preset the color space to obtain the second output color parameter; in the preset color space, adjust the second output color parameter according to the color deviation, the beautification color parameter, or the color deviation and the beautification color parameter, to obtain the third output color parameter ; Generate a target color lookup table according to the third output color parameter.

In a possible implementation manner, the color parameter components in the preset color space include: a hue component, a saturation component, and a lightness component; the generation module is configured to at least one of the following operations: according to the hue component of the beautification color parameter, Adjust the hue component of the second output color parameter to obtain the hue component of the third output color parameter; adjust the hue component of the second output color parameter according to the saturation component of the color deviation to obtain the saturation of the third output color parameter brightness component; according to the brightness component of the color deviation, the brightness component of the second output color parameter is adjusted to obtain the brightness component of the third output color parameter.

In a possible implementation manner, the generating module is configured to: when the third output color parameter belongs to a preset range, use the third output color parameter as the target output color parameter in the target color lookup table; When the color parameter exceeds the preset range, the target output color parameter in the target color lookup table is determined based on the critical color parameter in the preset range.

In a possible implementation, the beautification module is configured to: in the target color lookup table, look up the target output color parameter corresponding to the original color of the pixel in the target part as the initial target color of the pixel in the target part; The initial target color of the pixels in the target part is determined to determine the target color of the pixels in the target part; based on the original color and the target color of the pixels in the target part, a beautified face image is obtained.

In a possible implementation manner, the beautification module is configured to: when the processing type in the beautification operation includes natural processing, use the initial target color of the pixels in the target part as the target color of the pixels in the target part; or , when the processing type in the beautification operation includes metal light effect processing, the initial target color of the pixel in the target part is adjusted based on the randomly obtained noise value, and the target color of the pixel in the target part is obtained.

In a possible implementation manner, the beautification operation includes a lip makeup operation, and the target part includes a lip part.

Application Scenario Example

In the field of computer vision, how to obtain more realistic and natural lip makeup processed images has become an urgent problem to be solved.

The present disclosure proposes an image processing method based on the example of FIG. 11 , including the following process:

Step S111, receiving the beautification color parameter 10 (target_color) in RGB format input by the user on the input interface, the processing type selected on the input interface (such as water, highlight or matte 11 in Figure 11) and the input adjustment parameters (Intensity 12 and Brightness Intensity 13 in Figure 11, etc.).

Step S112, acquiring the face image 15 determined by the user by uploading photos and videos 14 or selecting a model.

Step S113, according to the beautification color parameter 10, adjust the preset color lookup table matched with the preset color parameter (lip_ref_color), so as to generate a target color lookup table. Wherein, the preset color parameter can be the primary color of the lips without any lip makeup treatment, and the process of generating the target color lookup table is as follows:

Traverse the multiple first output colors of the preset color lookup table, convert the multiple first output colors to the HSV color space (H is hue, S is saturation, V is brightness, all converted to the range of [0.0, 1.0] ), to obtain the second output color parameter (table_hsv) composed of a plurality of second output colors;

All the beautification color parameters and the preset color parameters are converted to the HSV color space, and the beautification color parameters (target_hsv) in the HSV color space and the preset color parameters (lip_ref_hsv) in the HSV color space are obtained;

Calculate the color deviation (diff) between the beautification color parameter and the preset color parameter in the preset color space through the formula (1) in the above-mentioned disclosed embodiment;

Through the formulas (2), (4) and (5) in the disclosed embodiments above, the H component, the S component and the V component of the target output color parameter are obtained, thereby obtaining the target output color parameter.

Step S114, using the lip mask image to obtain the image of the part where lip makeup needs to be done, based on the image of the part where lip makeup is to be done, extract the original color of the pixel of the lip makeup part in the face image, and based on the original color, search in the target color Look up in the table to get the target color 16 of the lip makeup part.

In step S115 , the searched target color and the original color are fused according to the intensity in the adjustment parameter input by the user to generate a beautified face image.

When the user clicks "Preview AR real-time makeup effect 17" in the input interface, the beautified face image is displayed in the input interface.

Through the application example of this disclosure, by receiving the beautification color parameters in the beautification operation, the user can be supported to choose the color value of the lip makeup arbitrarily, and a target color lookup table is generated based on the color value to realize the lip makeup operation, thereby greatly improving the user's choice of lip makeup. Effect degrees of freedom.

The image processing method proposed in the application example of this disclosure, in addition to being applied to the beautification operation of the lips in the face image, can also be extended to other parts of the beautification operation, such as blush or eye shadow, etc., with the beautification Depending on the type of operation, the image processing method proposed in the application examples of the present disclosure can be flexibly expanded and modified accordingly.

It can be understood that the above-mentioned method embodiments mentioned in this disclosure can all be combined with each other to form a combined embodiment without violating the principle and logic.

Those skilled in the art can understand that in the above-mentioned method of specific implementation, the writing order of each step does not imply a strict execution order and constitutes any limitation on the implementation process, and the execution order of each step should be based on its function and possible internal Logically OK.

Embodiments of the present disclosure also provide a computer-readable storage medium, on which computer program instructions are stored, and the above-mentioned method is implemented when the computer program instructions are executed by a processor. The computer readable storage medium may be a volatile computer readable storage medium or a nonvolatile computer readable storage medium.

An embodiment of the present disclosure also proposes an electronic device, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured as the above method.

In practical applications, the memory above can be a volatile memory (Volatile Memory), such as a random access memory (Random Access Memory, RAM); or a non-volatile memory (Non-Volatile Memory), such as a read-only memory (Read-Only Memory). Only Memory, ROM), flash memory (Flash Memory), hard disk (Hard Disk Drive, HDD) or solid-state drive (Solid-State Drive, SSD); or a combination of the above types of memory, and provide instructions and data to the processor .

The above-mentioned processor can be an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processing, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (programmable logic At least one of device, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor. It can be understood that, for different devices, the electronic device used to implement the above processor function may also be other, which is not limited in this embodiment of the present disclosure.

Electronic devices may be provided as terminals, servers, or other forms of devices.

Based on the same technical idea as the foregoing embodiments, the embodiments of the present disclosure further provide a computer program, which implements the above method when the computer program is executed by a processor.

FIG. 12 is a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be a terminal such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

As shown in FIG. 12 , the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (Input/Output, I/O) interface 812 , sensor component 814 , and communication component 816 .

The processing component 802 generally controls the overall operations of the electronic device 800, such as those associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802 .

The memory 804 is configured to store various types of data to support operations at the electronic device 800 . Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like.

The power supply component 806 provides power to various components of the electronic device 800 . Power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 800 .

The multimedia component 808 includes a screen providing an output interface between the electronic device 800 and the user. In some embodiments, the multimedia component 808 includes at least one of the following: a front camera and a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera, the rear camera, or the front camera and the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capability.

The audio component 810 is configured to output, input, or both output and input audio signals. For example, the audio component 810 includes a microphone (Microphone, MIC), and when the electronic device 800 is in an operation mode, such as a calling mode, a recording mode and a voice recognition mode, the microphone is configured to receive an external audio signal. Received audio signals may be stored in memory 804 or sent via communication component 816 . In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.

Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of electronic device 800 . For example, sensor assembly 814 may detect an open/closed state of electronic device 800, relative positioning of components, and the like.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.

In an exemplary embodiment, electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation for performing the methods described above.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to implement the above method.

The present disclosure may be at least one of the following: a system, a method, and a computer program product. A computer program product may include a computer readable storage medium having computer readable program instructions thereon for causing a processor to implement various aspects of the present disclosure.

A computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device via at least one of a network such as the Internet, a local area network, a wide area network, or a wireless network . A network adapter card or a network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for performing the operations of the present disclosure may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or programmed in at least one source or object code written in any combination of languages. Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.

Aspects of the present disclosure are described herein with reference to flowchart illustrations, block diagrams, or flowchart illustrations and block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowcharts, block diagrams, or both, and combinations of blocks in the flowcharts, block diagrams, or flowcharts and block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that when executed by the processor of the computer or other programmable data processing apparatus , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart, block diagram, or both the flowchart and the block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause at least one of the following, including: a computer, a programmable data processing device, and other equipment to work in a specific way, so that the computer that stores the instructions The readable medium then includes an article of manufacture including instructions for implementing various aspects of the functions/acts specified in the flowchart, block diagram, or one or more blocks in the flowchart and the block diagram.

It is also possible to load computer-readable program instructions into a computer, other programmable data processing device, or other equipment, so that a series of operational steps are performed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , so that instructions executed on computers, other programmable data processing devices, or other devices implement the functions/actions specified in the flowcharts, block diagrams, or one or more blocks in the flowcharts and block diagrams.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, a portion of a program segment, or an instruction that includes one or more Executable instructions. In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also to be noted that each block in the block diagrams, flowcharts, or both, and combinations of blocks in the block diagrams, flowcharts, or block diagrams and flowcharts, may be represented by special purpose components that perform the specified function or action. The implementation can be implemented by a hardware-based system, or it can be implemented by a combination of special purpose hardware and computer instructions.

Having described various embodiments of the present disclosure above, the foregoing description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and alterations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principle of each embodiment, practical application or technical improvement in the market, or to enable other ordinary skilled in the art to understand each embodiment disclosed herein.

Industrial Applicability

In an embodiment of the present disclosure, the image processing method includes: receiving a beautification operation on a target part of a human face image; generating a target that matches the beautification color parameter based on the beautification color parameters of the target part input in the beautification operation A color lookup table: generate a beautified face image according to the original color of the pixels in the target part of the face image and the target color lookup table. In the embodiment of the present disclosure, by receiving the beautification operation on the target part of the face image, and based on the beautification color parameters input in the beautification operation, a color lookup table corresponding to the beautification color parameter matching is generated, so that according to the target part of the face image The original color of the pixel and the target color lookup table to generate a beautified face image. Through the above process, the corresponding target color lookup table can be generated according to any input beautification color parameters in the beautification operation, so as to realize the beautification of the color of the target part. On the one hand, the color of the beautification operation can be enriched by any input beautification color parameters. Improve the freedom of beautification operation; on the other hand, the beautified face image can have a more natural beautification effect through the target color lookup table.

Claims

An image processing method, comprising:

Receive a beautification operation on the target part of the face image;

generating a target color lookup table matching the beautification color parameters based on the beautification color parameters of the target part input in the beautification operation;

A beautified human face image is generated according to the original color of the pixels in the target part of the human face image and the target color lookup table.
The method according to claim 1, wherein the generating a target color lookup table based on the beautification color parameters of the target part input in the beautification operation includes:

Acquiring a preset color lookup table, and preset color parameters corresponding to the preset color lookup table;

determining a color deviation between the beautification color parameters and the preset color parameters;

Based on the color deviation, the first output color parameter of the preset color lookup table is adjusted to obtain the target color lookup table.
The method according to claim 2, wherein the color deviation comprises a color deviation between the beautification color parameter and the preset color parameter in a preset color space;

The adjusting the first output color parameter of the preset color lookup table based on the color deviation to obtain the target color lookup table includes:

converting the first output color parameter in the preset color lookup table to the preset color space to obtain a second output color parameter;

In the preset color space, adjusting the second output color parameter according to the color deviation, the beautification color parameter, or the color deviation and the beautification color parameter, to obtain a third output color parameter ;

Generate the target color lookup table according to the third output color parameter.
The method according to claim 3, wherein the color parameter components in the preset color space include: a hue component, a saturation component, and a lightness component;

In the preset color space, adjusting the second output color parameter according to the color deviation, the beautification color parameter, or the color deviation and the beautification color parameter, to obtain a third output Color parameters, including at least one of the following operations:

adjusting the hue component of the second output color parameter according to the hue component of the beautification color parameter to obtain the hue component of the third output color parameter;

adjusting the hue component of the second output color parameter according to the saturation component of the color deviation to obtain the saturation component of the third output color parameter;

According to the brightness component of the color deviation, the brightness component of the second output color parameter is adjusted to obtain the brightness component of the third output color parameter.
The method according to claim 3 or 4, wherein said generating said target color lookup table according to said third output color parameter comprises:

When the third output color parameter belongs to a preset range, using the third output color parameter as a target output color parameter in the target color lookup table;

If the third output color parameter exceeds a preset range, the target output color parameter in the target color lookup table is determined based on a critical color parameter in the preset range.
The method according to any one of claims 1 to 5, wherein the beautified human face image is generated according to the original color of the pixels in the target part of the human face image and the target color lookup table, include:

In the target color lookup table, look up the target output color parameter corresponding to the original color of the pixel in the target part as the initial target color of the pixel in the target part;

determining the target color of the pixels in the target part according to the initial target color of the pixels in the target part;

Based on the original color of the pixels in the target part and the target color, a beautified human face image is determined.
The method according to claim 6, wherein said determining the target color of the pixels in the target part according to the initial target color of the pixels in the target part comprises:

When the processing type in the beautification operation includes natural processing, the initial target color of the pixels in the target part is used as the target color of the pixels in the target part; or,

In the case that the processing type in the beautification operation includes metal light effect processing, based on the randomly obtained noise value, the initial target color of the pixel in the target part is adjusted to obtain the target of the pixel in the target part color.
The method according to any one of claims 1 to 7, wherein the beautification operation includes a lip makeup operation, and the target site includes a lip site.
An image processing device, comprising:

The receiving module is configured to receive the beautification operation on the target part of the face image;

A generation module configured to generate a target color lookup table matching the beautification color parameters based on the beautification color parameters of the target part input in the beautification operation;

The beautification module is configured to generate a beautified face image according to the original color of the pixels in the target part of the face image and the target color lookup table.
An electronic device comprising:

processor;

memory for storing processor-executable instructions;

Wherein, the processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1-8.
A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 8 is realized.
A computer program product, comprising a computer-readable storage medium storing program codes, the instructions included in the program codes are executed by a processor of a computer device to implement the method according to any one of claims 1 to 8.