WO2016011747A1 - 肤色调整方法和装置 - Google Patents
肤色调整方法和装置 Download PDFInfo
- Publication number
- WO2016011747A1 WO2016011747A1 PCT/CN2014/091652 CN2014091652W WO2016011747A1 WO 2016011747 A1 WO2016011747 A1 WO 2016011747A1 CN 2014091652 W CN2014091652 W CN 2014091652W WO 2016011747 A1 WO2016011747 A1 WO 2016011747A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- preset
- skin color
- original
- value
- mean value
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/6027—Correction or control of colour gradation or colour contrast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/6075—Corrections to the hue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/62—Retouching, i.e. modification of isolated colours only or in isolated picture areas only
- H04N1/628—Memory colours, e.g. skin or sky
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/643—Hue control means, e.g. flesh tone control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2215/00—Indexing scheme for image rendering
- G06T2215/16—Using real world measurements to influence rendering
Definitions
- the present disclosure relates to the field of image processing, and more particularly to a skin color adjustment method and apparatus.
- the current mobile terminal can adjust the skin color in the image when the image is beautified, for example, the user selects the target color, and the mobile terminal converts the color of the skin color region in the image into the target color.
- the inventors have found that the related art has defects, for example, the degree of recognition of the color by the human eye is limited, and when the target color is selected only by the user, there is a big gap between the converted skin color and the actual skin color, and the image is easy. Distortion, beautification effect is poor.
- the present disclosure provides a skin color adjustment method and apparatus.
- the technical solution is as follows:
- a skin color adjustment method comprising:
- the skin color region is adjusted according to the target color data.
- selecting, according to the original mean value and the preset mean value of the at least one preset skin color model, selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model comprises:
- selecting, according to the original mean value and the preset mean value of the at least one preset skin color model, selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model comprises:
- the color data is YUV data
- the target color is determined according to the original color data, the original mean value and the original standard deviation, a preset mean value of the specified skin color model, and a preset standard deviation.
- the data includes:
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the The value of the original color data on the dimension V in the YUV space
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * The value of the target color data in the dimension V in the YUV space
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the YUV space The value on dimension V;
- deltaY is the value of the original standard deviation in the dimension Y in the YUV space
- deltaU is the value of the original standard deviation in the dimension U in the YUV space
- deltaV is the original standard deviation The value on the dimension V in the YUV space
- meanY iType is the value of the preset mean value in the dimension Y in the YUV space
- meanU iType is the value of the preset mean value in the dimension U in the YUV space
- meanV iType is a value of the preset mean value in the dimension V in the YUV space
- deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space
- the deltaU iType is the dimension of the preset standard deviation in the dimension U in the YUV space
- the value, deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the adjusting the skin color region according to the target color data includes:
- the original color data of each pixel in the skin color region is adjusted to the target color data of each pixel.
- the at least one preset skin color model includes a first preset skin color model, a second preset skin color model, a third preset skin color model, a fourth preset skin color model, a fifth preset skin color model, and a sixth Preset skin color model;
- the preset mean value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light white sample image;
- the preset mean value and the preset standard deviation of the second preset skin color model are obtained according to the color data of the dark Caucasian sample image;
- the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image;
- the preset mean value and the preset standard deviation of the fourth preset skin color model are obtained according to the color data of the dark yellow human sample image;
- the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image;
- the preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
- a skin tone adjusting device comprising:
- a skin color region identification module for identifying a skin color region of the image
- a statistic module configured to perform statistics on original color data of the pixel points in the skin color region, to obtain an original mean value and an original standard deviation of the pixel points in the skin color region;
- a skin color model specifying module configured to select, according to the original mean value and a preset mean value of the at least one preset skin color model, a specified skin color model most similar to the skin color region from the at least one preset skin color model, the pre-predetermined Set the skin color model to represent the skin color type;
- a target color determining module configured to determine target color data according to the original color data, the original mean value and the original standard deviation, a preset mean value of the specified skin color model, and a preset standard deviation;
- a skin color adjustment module configured to adjust the skin color region according to the target color data.
- the skin color model specifying module includes:
- a similarity calculation unit configured to calculate a difference between the original mean value and a preset mean value of the at least one preset skin color model
- a skin color model selecting unit configured to select a specified skin color model from the at least one preset skin color model, wherein a difference between a preset mean value of the specified skin color model and the original mean value is the smallest.
- the skin color model specifying module includes:
- a Euclidean distance calculating unit configured to calculate an Euclidean distance between the original mean value and the at least one preset mean value
- the skin color model selecting unit is further configured to select a specified skin color model from the at least one preset skin color model, wherein a Euclidean distance between the preset mean value of the specified skin color model and the original average value is the smallest.
- the device uses YUV data as the color data
- the target color determining module configured, for each pixel point in the skin color region, according to original color data of the pixel point, the original mean value, and the original standard deviation, the preset of the specified skin color model Mean and preset standard deviation, the following formula is used to determine the target color data of the pixel:
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the The value of the original color data on the dimension V in the YUV space
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * The value of the target color data in the dimension V in the YUV space
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the YUV space The value on dimension V;
- deltaY is the value of the original standard deviation in the dimension Y in the YUV space
- deltaU is the value of the original standard deviation in the dimension U in the YUV space
- deltaV is the original standard deviation The value on the dimension V in the YUV space
- meanY iType is the value of the preset mean value in the dimension Y in the YUV space
- meanU iType is the value of the preset mean value in the dimension U in the YUV space
- meanV iType is a value of the preset mean value in the dimension V in the YUV space
- deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space
- the deltaU iType is the dimension of the preset standard deviation in the dimension U in the YUV space
- the value, deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the skin color adjustment module includes:
- a skin color adjusting unit configured to adjust original color data of each pixel point in the skin color region to target color data of each pixel point.
- the device further includes:
- a skin color type preset module configured to set the at least one preset skin color type, the at least one preset skin color model includes a first preset skin color model, a second preset skin color model, and a third preset skin color model, Four preset skin color models, a fifth preset skin color model, and a sixth preset skin color model;
- the preset mean value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light white sample image;
- the preset mean value and the preset standard deviation of the second preset skin color model are obtained according to the color data of the dark Caucasian sample image;
- the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image;
- the preset mean value and the preset standard deviation of the fourth preset skin color model are obtained according to the color data of the dark yellow human sample image;
- the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image;
- the preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
- a skin color adjusting device including:
- a memory for storing processor executable instructions
- processor is configured to:
- the skin color region is adjusted according to the target color data.
- the method and apparatus provided in this embodiment selects a specified skin color model that is most similar to the skin color region by counting the original color data of the pixel points in the skin color region, according to the original color data, the original mean value, and the original standard deviation, the designation.
- the preset average value of the skin color model and the preset standard deviation determine the target color data, and the skin color region is adjusted according to the target color data.
- the skin color area is adjusted based on the specified skin color model, the adjusted The difference between the skin color and the actual skin color, to avoid distortion of the image, improve the beautification effect, without the user to select the target color, the operation is simple, and the algorithm is simple and easy to implement.
- FIG. 1 is a flowchart of a skin color adjusting method according to an exemplary embodiment
- FIG. 2 is a flowchart of a skin color adjusting method according to an exemplary embodiment
- FIG. 3 is a block diagram of a skin color adjusting device according to an exemplary embodiment
- FIG. 4 is a block diagram of an apparatus for skin tone adjustment, according to an exemplary embodiment
- FIG. 5 is a block diagram of another apparatus for skin tone adjustment, according to an exemplary embodiment.
- Embodiments of the present disclosure provide a skin color adjustment method and apparatus, which will be described in detail below with reference to the accompanying drawings.
- FIG. 1 is a flowchart of a skin color adjusting method according to an exemplary embodiment. As shown in FIG. 1 , the method includes the following steps:
- step 101 the skin color region of the image is identified.
- step 102 the original color data of the pixel points in the skin color region is counted to obtain the original mean value and the original standard deviation of the pixel points in the skin color region.
- step 103 according to the original mean value and the preset mean value of the at least one preset skin color model, a specified skin color model most similar to the skin color region is selected from the at least one preset skin color model, and the preset skin color model is used to represent Skin type.
- target color data is determined based on the original color data, the original mean and the original standard deviation, a preset mean of the specified skin color model, and a preset standard deviation.
- step 105 the skin color region is adjusted according to the target color data.
- the method provided in this embodiment selects a specified skin color model that is most similar to the skin color region by counting the original color data of the pixel points in the skin color region, according to the original color data, the original mean value, and the original standard deviation, the specified skin color model.
- the preset average value and the preset standard deviation determine the target color data, and the skin color region is adjusted according to the target color data.
- selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model according to the original mean value and the preset mean value of the at least one preset skin color model includes:
- a specified skin color model is selected from the at least one preset skin color model, and a difference between the preset mean value of the specified skin color model and the original mean value is the smallest.
- selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model according to the original mean value and the preset mean value of the at least one preset skin color model includes:
- a specified skin color model is selected from the at least one preset skin color model, and the Euclidean distance between the preset mean value of the specified skin color model and the original mean value is the smallest.
- the color data is YUV data
- determining the target color data according to the original color data, the original mean value and the original standard deviation, the preset mean value of the specified skin color model, and the preset standard deviation, the determining the target color data includes:
- Target color data for points For each pixel in the skin color region, according to the original color data of the pixel, the original mean and the original standard deviation, the preset mean of the specified skin model, and the preset standard deviation, the following formula is applied to determine the pixel.
- Target color data for points :
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the original color data.
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * is the target The value of the color data in the dimension V in the YUV space
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the dimension V of the YUV space Value
- deltaY is the value of the original standard deviation in the dimension Y of the YUV space
- deltaU is the value of the original standard deviation in the dimension U of the YUV space
- the deltaV is the original standard deviation in the YUV space.
- meanY iType is the value of the preset mean value in the dimension Y of the YUV space
- meanU iType is the value of the preset mean value in the dimension U of the YUV space
- meanV iType is the value The value of the preset mean in the dimension V in the YUV space
- deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space
- the deltaU iType is the value of the preset standard deviation in the dimension U in the YUV space
- deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the adjusting the skin color region according to the target color data includes:
- the original color data of each pixel in the skin color region is adjusted to the target color data of each pixel.
- the at least one preset skin color model includes a first preset skin color model, a second preset skin color model, a third preset skin color model, a fourth preset skin color model, a fifth preset skin color model, and a sixth pre-pre Set the skin color model;
- the preset mean value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light white sample image;
- the preset mean value and the preset standard deviation of the second preset skin color model are obtained according to the color data of the dark Caucasian sample image;
- the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image;
- the preset mean value and the preset standard deviation of the fourth preset skin color model are obtained according to the color data of the dark yellow sample image;
- the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image;
- the preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
- FIG. 2 is an exemplary flowchart of a skin color adjustment method.
- the skin color adjustment method is used in a server, and includes the following steps:
- the server identifies a skin color region of the image, and performs statistics on the original color data of the pixel points in the skin color region to obtain a raw mean value and an original standard deviation of the pixel points in the skin color region.
- the image may be an image uploaded to the server after the terminal is photographed, or may be an image sent to the server by another server.
- the image includes a skin color region, and may include a person. The face area, or the whole body area of the person, etc., is not limited in this embodiment.
- the terminal captures an image, it can be automatically uploaded to the server, and the server performs skin color adjustment on the image, and then sends the image to the terminal, the terminal directly displays the adjusted image, or the terminal displays the captured image, when the user triggers the pair.
- the image is adjusted by the skin color adjustment command
- the terminal uploads the image to the server, and the server performs skin color adjustment on the image, and then sends the image to the terminal, and the terminal displays the adjusted image again.
- This embodiment does not do this either. limited.
- the server uses the skin color detection algorithm to identify the image, selects a sample pixel of the image according to the skin color detection operator, uses a Gaussian mixture model to color the skin color, and applies the established color model, The skin color region and the non-skin color region in the image are classified to obtain a skin color region of the image.
- the server may identify a plurality of skin color regions of the image, such as a forehead skin color region, a cheek skin color region, and a nose skin color region in the face image, and the server performs skin color adjustment for each skin color region, respectively.
- a skin color region of the image will be described as an example.
- the server may select a plurality of sample pixel points in the skin color region, obtain original color data of each sample pixel point, and perform statistics on the original color data of the plurality of sample pixel points to obtain the plurality of The mean and standard deviation of the original color data of the sample pixel as the original mean and original standard deviation of the pixel points in the skin color region.
- the original mean value obtained by the server is The original standard deviation is In the three-dimensional space of YUV, the detection result of the skin color region is an ellipsoid, and the original mean is an ellipsoidal sphere, and the three elements in the original standard deviation are the three sphere radii of the ellipsoid.
- the server calculates a similarity between the original mean value and a preset mean value of the at least one preset skin color model, and selects a specified skin color model from the at least one preset skin color model, where the preset mean value of the specified skin color model is The similarity between the original mean values is the largest, and the preset mean value and the preset standard deviation of the specified skin color model are determined.
- the server pre-establishes the at least one preset skin color model, and acquires a preset average value and a preset standard deviation of the at least one preset skin color model.
- Each preset skin color model is used to represent a skin color type, and the server can determine a specified skin color type most similar to the skin color region according to the similarity between the original mean value and the preset mean value of the at least one preset skin color model When adjusting based on the specified skin color type, the difference between the adjusted skin color and the actual skin color can be reduced to avoid image distortion.
- the method further comprises: the server establishing the at least one preset skin color model. Specifically, the server selects sample images of different skin color types. For each skin color type, the server performs training statistics and modeling on color data of multiple sample images belonging to the skin color type, and obtains a preset corresponding to the skin color type. The skin color model, and the mean and standard deviation of the preset skin color model, as the preset mean value and the preset standard deviation of the preset skin color model. The process of performing statistics on each sample picture is similar to the step 201, and details are not described herein again.
- the preset skin color model is an ellipsoid
- the preset mean value is the spherical center of the ellipsoid
- the three elements in the preset standard deviation are the three sphere radii of the ellipsoid.
- the server may perform offline statistics on the color data of the plurality of sample images, that is, when the preset mean value and the preset standard deviation of the preset skin color model are obtained, the color data of the sample image is deleted to save storage space. .
- the selection of the sample image is as follows: the skin color region in the sample image is clear and beautiful, so as to ensure that the skin color region of the skin color region is not subject to distortion after the skin color region is adjusted according to the specified skin color model. Meet the user's beautification needs.
- the human skin color type is divided into light color white, dark white, light yellow yellow, dark yellow, light black, dark black, the server according to the above six
- the sample images of the skin color types are separately counted, and six preset skin color models are created: a first preset skin color model, a second preset skin color model, a third preset skin color model, a fourth preset skin color model, and a fifth preset.
- Skin color model and sixth preset skin color model are created.
- the preset average value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light color white sample image; the preset average value and the preset standard deviation of the second preset skin color model are according to the dark color.
- the color data of the white sample image is statistically obtained; the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image; the preset of the fourth preset skin color model The mean value and the preset standard deviation are obtained according to the color data of the dark yellow human sample image; the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image; The preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
- the server calculates a similarity between the original mean value and the at least one preset skin color model, and the greater the similarity, the more similar the skin color region is to the corresponding preset skin color model, the server The preset skin color model having the largest similarity between the preset mean value and the original mean value is selected in the at least one preset skin color model as the specified skin color model, and the specified skin color model is the skin color model most similar to the skin color region. For example, when the skin color region is a light color yellow person's skin color region, the server determines a preset mean value of the third preset skin color model by calculating a similarity between the original mean value and the at least one preset mean value. If the similarity between the original average values is the largest, the third preset skin color model is used as the specified skin color model, and the skin color region is adjusted according to the third skin color model.
- the server calculates an Euclidean distance between the original mean value and the at least one preset mean value, and the smaller the Euclidean distance, the more similar the skin color region is to the corresponding preset skin color model, from the at least one preset skin color.
- the specified skin color model is selected in the model, and the Euclidean distance between the preset mean value of the specified skin color model and the original mean value is the smallest. That is, the specified formula is determined by applying the following formula:
- n the number of preset skin color models
- Two vectors with The Euclidean distance between the two is the specified skin color model, and the Euclidean distance between the preset mean value of the specified skin color model and the original mean value is the smallest.
- the server calculates a cosine similarity between the original mean and the at least one preset mean, and the greater the cosine similarity, the more similar the skin color region is to the corresponding preset skin color model, from the at least one preset skin color
- the specified skin color model is selected in the model, and the cosine similarity between the preset mean value of the specified skin color model and the original mean value is the largest.
- This embodiment does not limit the type of similarity.
- the server may further calculate a difference between the original mean value and the at least one preset mean value, and the smaller the difference is, the more the skin color region and the corresponding preset skin color model are represented. Similarly, selecting a specified skin color model from the at least one preset skin color model, the preset mean value of the specified skin color model and the original mean value The difference is the smallest.
- the server determines target color data according to the original color data, the original mean value and the original standard deviation, a preset mean value of the specified skin color model, and a preset standard deviation, and adjusts the skin color region according to the target color data. .
- the original color data is YUV data
- the server is based on the original color data of the pixel, the original mean and the original standard deviation, and the preset of the specified skin color model.
- Mean and preset standard deviation the following formula is used to determine the target color data of the pixel:
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the original color data.
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * is the target
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the dimension V of the YUV space Value
- deltaY is the value of the original standard deviation in the dimension Y of the YUV space
- deltaU is the value of the original standard deviation in the dimension Y of the YUV space
- deltaU is the value of the original standard deviation
- the value on dimension V For the preset mean value of the specified skin color model, The value of the preset mean value in the dimension Y in the YUV space, the meanU iType is the value of the preset mean value in the dimension U of the YUV space, and the meanV iType is the value of the preset mean value in the dimension V of the YUV space. value; For the preset standard deviation of the specified skin color model, deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space, and the deltaU iType is the value of the preset standard deviation in the dimension U in the YUV space, deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the server may obtain the following formula according to the above formula, and apply the following formula to determine the target color data of the pixel:
- the server determines the target color data of each pixel in the skin color region
- the original color data of each pixel is adjusted to the corresponding target color data, and the skin color adjustment is realized.
- the original color data of the pixel points in the skin color region is counted, and according to the similarity of the skin color model, the specified skin color model most similar to the skin color region is intelligently selected from the at least one preset skin color model.
- the skin color adjustment is performed based on the specified skin color model, which reduces the difference between the adjusted skin color and the actual skin color, avoids image distortion, and is simple and easy to implement.
- the execution subject is taken as an example of the server, and in fact, the execution entity may also be a terminal, and the terminal downloads a preset average value and preset of at least one preset skin color model established by the server.
- the standard deviation is used to adjust the skin color of the skin color region of the image when the image is captured by the terminal. This embodiment does not limit the execution body.
- the method provided in this embodiment selects a specified skin color model that is most similar to the skin color region by counting the original color data of the pixel points in the skin color region, according to the original color data, the original mean value, and the original standard deviation, the specified skin color model.
- the preset average value and the preset standard deviation determine the target color data, and the skin color region is adjusted according to the target color data.
- FIG. 3 is a block diagram of a skin tone adjusting device according to an exemplary embodiment.
- the device includes a skin color region identification module 301, a statistics module 302, a skin color model specifying module 303, a target color determining module 304, and a skin color adjusting module 305.
- the skin color region identification module 301 is configured to identify a skin color region of the image
- the statistic module 302 is configured to perform statistics on the original color data of the pixel points in the skin color region to obtain the original mean value and the original standard deviation of the pixel points in the skin color region;
- the skin color model specifying module 303 is configured to select, according to the original mean value and a preset mean value of the at least one preset skin color model, a specified skin color model that is most similar to the skin color region from the at least one preset skin color model, the pre Set the skin color model to represent the skin color type;
- the target color determining module 304 is configured to determine target color data according to the original color data, the original mean value and the original standard deviation, a preset mean value of the specified skin color model, and a preset standard deviation;
- the skin tone adjustment module 305 is configured to adjust the skin color region according to the target color data.
- the skin color model specifying module 303 includes:
- a similarity calculation unit configured to calculate between the original mean value and a preset mean value of the at least one preset skin color model Difference
- a skin color model selecting unit configured to select a specified skin color model from the at least one preset skin color model, wherein a difference between the preset mean value of the specified skin color model and the original average value is the smallest.
- the skin color model specifying module 303 includes:
- An Euclidean distance calculation unit configured to calculate an Euclidean distance between the original mean value and the at least one preset mean value
- the skin color model selecting unit is further configured to select a specified skin color model from the at least one preset skin color model, and the Euclidean distance between the preset mean value of the specified skin color model and the original average value is the smallest.
- the color data is YUV data
- the target color determining module 304 is configured to: for each pixel in the skin color region, according to the original color data of the pixel, the original mean, and the original standard deviation, Specify the preset mean and preset standard deviation of the skin color model, and use the following formula to determine the target color data of the pixel:
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the original color data.
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * is the target The value of the color data in the dimension V in the YUV space
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the dimension V of the YUV space Value
- deltaY is the value of the original standard deviation in the dimension Y of the YUV space
- deltaU is the value of the original standard deviation in the dimension U of the YUV space
- the deltaV is the original standard deviation in the YUV space.
- meanY iType is the value of the preset mean value in the dimension Y of the YUV space
- meanU iType is the value of the preset mean value in the dimension U of the YUV space
- meanV iType is the value The value of the preset mean in the dimension V in the YUV space
- deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space
- the deltaU iType is the value of the preset standard deviation in the dimension U in the YUV space
- deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the skin color adjustment module 305 includes:
- a skin color adjusting unit configured to adjust original color data of each pixel in the skin color region to target color data of each pixel.
- the device further includes:
- a skin color type preset module configured to set the at least one preset skin color type, the at least one preset skin color model comprising a first preset skin color model, a second preset skin color model, a third preset skin color model, and a fourth pre- Setting a skin color model, a fifth preset skin color model, and a sixth preset skin color model;
- the preset mean value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light white sample image;
- the preset mean value and the preset standard deviation of the second preset skin color model are obtained according to the color data of the dark Caucasian sample image;
- the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image;
- the preset mean value and the preset standard deviation of the fourth preset skin color model are obtained according to the color data of the dark yellow sample image;
- the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image;
- the preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
- the skin color adjusting device provided in the above embodiment is only exemplified by the division of the above functional modules when adjusting the skin color. In actual applications, the function distribution may be completed by different functional modules as needed.
- the internal structure of the server is divided into different functional modules to perform all or part of the functions described above.
- the skin color adjusting device and the skin color adjusting method embodiment are provided in the same concept, and the specific implementation process is described in detail in the method embodiment, and details are not described herein again.
- FIG. 4 is a block diagram of an apparatus 400 for skin tone adjustment, according to an exemplary embodiment.
- device 400 can be provided as a server.
- apparatus 400 includes a processing component 422 that further includes one or more processors, and memory resources represented by memory 432 for storing instructions executable by processing component 422, such as an application.
- An application stored in memory 432 may include one or more modules each corresponding to a set of instructions.
- processing component 422 is configured to execute instructions, To perform the above skin color adjustment method.
- Device 400 may also include a power supply component 426 configured to perform power management of device 400, a wired or wireless network interface 450 configured to connect device 400 to the network, and an input/output (I/O) interface 458.
- Device 400 can operate based on an operating system stored in memory 432, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
- FIG. 5 is a block diagram of another apparatus 500 for skin tone adjustment, according to an exemplary embodiment.
- device 500 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
- apparatus 500 can include one or more of the following components: processing component 502, memory 504, power component 506, multimedia component 508, audio component 510, input/output (I/O) interface 512, sensor component 514, And a communication component 516.
- Processing component 502 typically controls the overall operation of device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
- Processing component 502 can include one or more processors 520 to execute instructions to perform all or part of the steps of the above described methods.
- processing component 502 can include one or more modules to facilitate interaction between component 502 and other components.
- processing component 502 can include a multimedia module to facilitate interaction between multimedia component 508 and processing component 502.
- Memory 504 is configured to store various types of data to support operation at device 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phone book data, messages, pictures, videos, and the like.
- the memory 504 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable.
- SRAM static random access memory
- EEPROM electrically erasable programmable read only memory
- EPROM Electrically erasable programmable read only memory
- PROM Programmable Read Only Memory
- ROM Read Only Memory
- Magnetic Memory Flash Memory
- Disk Disk or Optical Disk.
- Power component 506 provides power to various components of device 500.
- Power component 506 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 500.
- the multimedia component 508 includes a screen between the device 500 and the user that provides an output interface.
- the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
- the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
- the multimedia component 508 includes a front camera and/or a rear camera. When the device 500 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
- the audio component 510 is configured to output and/or input an audio signal.
- audio component 510 includes a Microphone (MIC), when the device 500 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal.
- the received audio signal may be further stored in memory 504 or transmitted via communication component 516.
- audio component 510 also includes a speaker for outputting an audio signal.
- the I/O interface 512 provides an interface between the processing component 502 and the peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.
- Sensor assembly 514 includes one or more sensors for providing device 500 with various aspects of status assessment.
- sensor component 514 can detect an open/closed state of device 500, a relative positioning of components, such as the display and keypad of device 500, and sensor component 514 can also detect a change in position of one component of device 500 or device 500. The presence or absence of user contact with device 500, device 500 orientation or acceleration/deceleration, and temperature variation of device 500.
- Sensor assembly 514 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
- Sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
- the sensor component 514 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
- Communication component 516 is configured to facilitate wired or wireless communication between device 500 and other devices.
- the device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
- communication component 516 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
- the communication component 516 also includes a near field communication (NFC) module to facilitate short range communication.
- NFC near field communication
- the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
- RFID radio frequency identification
- IrDA infrared data association
- UWB ultra-wideband
- Bluetooth Bluetooth
- apparatus 500 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 gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
- ASICs application specific integrated circuits
- DSPs digital signal processors
- DSPDs digital signal processing devices
- PLDs programmable logic devices
- FPGA field programmable A gate array
- controller microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
- non-transitory computer readable storage medium comprising instructions, such as a memory 504 comprising instructions executable by processor 520 of apparatus 500 to perform the above method.
- the non-transitory computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
- a non-transitory computer readable storage medium when instructions in the storage medium are executed by a processor of a mobile terminal, enabling the mobile terminal to perform a skin tone adjustment method, the method comprising:
- the original color data of the pixel points in the skin color region is counted to obtain the original average of the pixel points in the skin color region. Value and original standard deviation;
- the skin color region is adjusted based on the target color data.
- selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model according to the original mean value and the preset mean value of the at least one preset skin color model includes:
- a specified skin color model is selected from the at least one preset skin color model, and a difference between the preset mean value of the specified skin color model and the original mean value is the smallest.
- selecting the specified skin color model that is most similar to the skin color region from the at least one preset skin color model according to the original mean value and the preset mean value of the at least one preset skin color model includes:
- a specified skin color model is selected from the at least one preset skin color model, and the Euclidean distance between the preset mean value of the specified skin color model and the original mean value is the smallest.
- the color data is YUV data
- determining the target color data according to the original color data, the original mean value and the original standard deviation, the preset mean value of the specified skin color model, and the preset standard deviation, the determining the target color data includes:
- Target color data for points For each pixel in the skin color region, according to the original color data of the pixel, the original mean and the original standard deviation, the preset mean of the specified skin model, and the preset standard deviation, the following formula is applied to determine the pixel.
- Target color data for points :
- Y is the value of the original color data in the dimension Y in the YUV space
- U is the value of the original color data in the dimension U in the YUV space
- V is the original color data.
- Y * is the value of the target color data in the dimension Y in the YUV space
- U * is the value of the target color data in the dimension U in the YUV space
- V * is the target The value of the color data in the dimension V in the YUV space
- meanY is the value of the original mean in the dimension Y in the YUV space
- meanU is the value of the original mean in the dimension U in the YUV space
- meanV is the original mean in the dimension V of the YUV space Value
- deltaY is the value of the original standard deviation in the dimension Y of the YUV space
- deltaU is the value of the original standard deviation in the dimension U of the YUV space
- the deltaV is the original standard deviation in the YUV space.
- meanY iType is the value of the preset mean value in the dimension Y of the YUV space
- meanU iType is the value of the preset mean value in the dimension U of the YUV space
- meanV iType is the value The value of the preset mean in the dimension V in the YUV space
- deltaY iType is the value of the preset standard deviation in the dimension Y in the YUV space
- the deltaU iType is the value of the preset standard deviation in the dimension U in the YUV space
- deltaV iType is the value of the preset standard deviation on the dimension V in the YUV space.
- the adjusting the skin color region according to the target color data includes:
- the original color data of each pixel in the skin color region is adjusted to the target color data of each pixel.
- the at least one preset skin color model includes a first preset skin color model, a second preset skin color model, a third preset skin color model, a fourth preset skin color model, a fifth preset skin color model, and a sixth pre-pre Set the skin color model;
- the preset mean value and the preset standard deviation of the first preset skin color model are obtained according to the color data of the light white sample image;
- the preset mean value and the preset standard deviation of the second preset skin color model are obtained according to the color data of the dark Caucasian sample image;
- the preset mean value and the preset standard deviation of the third preset skin color model are obtained according to the color data of the light yellow yellow sample image;
- the preset mean value and the preset standard deviation of the fourth preset skin color model are obtained according to the color data of the dark yellow sample image;
- the preset mean value and the preset standard deviation of the fifth preset skin color model are obtained according to the color data of the light black sample image;
- the preset mean value and the preset standard deviation of the sixth preset skin color model are obtained according to the color data of the dark black sample image.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
本公开是关于一种肤色调整方法和装置，属于图像处理领域。该方法包括：识别图像的肤色区域；对该肤色区域中像素点的原始颜色数据进行统计，得到该肤色区域中像素点的原始均值和原始标准差；根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型，该预设肤色模型用于表示肤色类型；根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据；根据该目标颜色数据，对该肤色区域进行调整。本公开减小了调整后的肤色与实际肤色的差距，避免图像出现失真，提高美化效果，无需用户选择目标颜色，操作简便，且算法简单，易于实现。
Description
本申请基于申请号为201410351282.X、申请日为2014年7月23日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
本公开是关于图像处理领域，具体来说是关于肤色调整方法和装置。
随着图像处理技术的发展和用户需求的提升，对所拍摄的图像进行美化处理已经成为移动终端必不可少的功能。
目前的移动终端在对图像进行美化处理时，可以对图像中的肤色进行调整，如，由用户选择目标颜色，移动终端将图像中的肤色区域的颜色转换为该目标颜色。
在实现本公开的过程中，发明人发现相关技术存在缺陷，例如：人眼对颜色的识别程度有限，仅由用户选择目标颜色时，转换后的肤色与实际肤色存在很大的差距，图像容易失真，美化效果较差。
发明内容
为了解决相关技术中存在的问题，本公开提供了一种肤色调整方法和装置。所述技术方案如下：
根据本公开实施例的第一方面，提供了一种肤色调整方法，所述方法包括：
识别图像的肤色区域；
对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；
根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；
根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；
根据所述目标颜色数据，对所述肤色区域进行调整。
可选的，所述根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型包括：
计算所述原始均值与所述至少一个预设肤色模型的预设均值之间的差值；
从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的差值最小。
可选的，所述根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型包括：
计算所述原始均值与所述至少一个预设均值之间的欧式距离；
从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的欧式距离最小。
可选的，所述颜色数据为YUV数据，所述根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据包括：
对于所述肤色区域中的每个像素点，根据所述像素点的原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，应用以下公式，确定所述像素点的目标颜色数据：
其中，
为所述像素点的原始颜色数据，Y为所述原始颜色数据在YUV空间中维度Y上的取值，U为所述原始颜色数据在YUV空间中维度U上的取值，V为所述原始颜色数据在YUV空间中维度V上的取值；
可选的，所述根据所述目标颜色数据，对所述肤色区域进行调整包括：
将所述肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
可选的，所述至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；
所述第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；
所述第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；
所述第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；
所述第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；
所述第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；
所述第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
根据本公开实施例的第二方面，提供了一种肤色调整装置，所述装置包括：
肤色区域识别模块，用于识别图像的肤色区域；
统计模块，用于对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；
肤色模型指定模块，用于根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；
目标颜色确定模块，用于根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；
肤色调整模块，用于根据所述目标颜色数据，对所述肤色区域进行调整。
可选的，所述肤色模型指定模块包括：
相似度计算单元，用于计算所述原始均值与所述至少一个预设肤色模型的预设均值之间的差值；
肤色模型选取单元，用于从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的差值最小。
所述肤色模型指定模块包括：
欧式距离计算单元，用于计算所述原始均值与所述至少一个预设均值之间的欧式距离；
所述肤色模型选取单元，还用于从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的欧式距离最小。
可选的，所述装置采用YUV数据作为所述颜色数据；
所述目标颜色确定模块，用于对于所述肤色区域中的每个像素点，根据所述像素点的原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，应用以下公式，确定所述像素点的目标颜色数据：
其中，
为所述像素点的原始颜色数据，Y为所述原始颜色数据在YUV空间中维度Y上的取值，U为所述原始颜色数据在YUV空间中维度U上的取值，V为所述原始颜色数据在YUV空间中维度V上的取值；
可选的，所述肤色调整模块包括：
肤色调整单元，用于将所述肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
可选的，所述装置还包括：
肤色类型预设模块，用于设定所述至少一个预设肤色类型，所述至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；
所述第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；
所述第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；
所述第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；
所述第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；
所述第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；
所述第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
根据本公开实施例的第三方面，提供了一种肤色调整装置，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为：
识别图像的肤色区域；
对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；
根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；
根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；
根据所述目标颜色数据，对所述肤色区域进行调整。
本公开的实施例提供的技术方案可以包括以下有益效果：
本实施例提供的方法和装置，通过对肤色区域中像素点的原始颜色数据进行统计后选取与该肤色区域最相似的指定肤色模型，根据该原始颜色数据、原始均值和原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据，根据该目标颜色数据对该肤色区域进行调整。在该指定肤色模型的基础上对肤色区域进行调整时，减小了调整后的
肤色与实际肤色的差距，避免图像出现失真，提高美化效果，无需用户选择目标颜色，操作简便，且算法简单，易于实现。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性的，并不能限制本公开。
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本发明的实施例，并与说明书一起用于解释本发明的原理。
图1是根据一示例性实施例示出的一种肤色调整方法的流程图；
图2是根据一示例性实施例示出的一种肤色调整方法的流程图；
图3是根据一示例性实施例示出的一种肤色调整装置的框图；
图4是根据一示例性实施例示出的一种用于肤色调整的装置的框图；
图5是根据一示例性实施例示出的另一种用于肤色调整的装置的框图。
为使本公开的目的、技术方案和优点更加清楚明白，下面结合实施方式和附图，对本公开做进一步详细说明。在此，本公开的示意性实施方式及其说明用于解释本公开，但并不作为对本公开的限定。
本公开实施例提供一种肤色调整方法和装置，以下结合附图对本公开进行详细说明。
图1是根据一示例性实施例示出的一种肤色调整方法的流程图，如图1所示，包括以下步骤：
在步骤101中，识别图像的肤色区域。
在步骤102中，对该肤色区域中像素点的原始颜色数据进行统计，得到该肤色区域中像素点的原始均值和原始标准差。
在步骤103中，根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型，该预设肤色模型用于表示肤色类型。
在步骤104中，根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据。
在步骤105中，根据该目标颜色数据，对该肤色区域进行调整。
本实施例提供的方法，通过对肤色区域中像素点的原始颜色数据进行统计后选取与该肤色区域最相似的指定肤色模型，根据该原始颜色数据、原始均值和原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据，根据该目标颜色数据对该肤色区域进行调整。在该指定肤色模型的基础上对肤色区域进行调整时，减小了调整后的肤色与实际肤色的差距，避免图像出现失真，提高美化效果，无需用户选择目标颜色，操作简便，
且算法简单，易于实现。
可选的，该根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型包括：
计算该原始均值与该至少一个预设肤色模型的预设均值之间的差值；
从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的差值最小。
可选的，该根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型包括：
计算该原始均值与该至少一个预设均值之间的欧式距离；
从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的欧式距离最小。
可选的，该颜色数据为YUV数据，该根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据包括：
对于该肤色区域中的每个像素点，根据该像素点的原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，应用以下公式，确定该像素点的目标颜色数据：
其中，
为该像素点的原始颜色数据，Y为该原始颜色数据在YUV空间中维度Y上的取值，U为该原始颜色数据在YUV空间中维度U上的取值，V为该原始颜色数据在YUV空间中维度V上的取值；
可选的，该根据该目标颜色数据，对该肤色区域进行调整包括：
将该肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
可选的，该至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；
该第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；
该第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；
该第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；
该第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；
该第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；
该第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
上述所有可选技术方案，可以采用任意结合形成本发明的可选实施例，在此不再一一赘述。
在一个实施例中，图2是肤色调整方法的示例性流程图，参见图2，该肤色调整方法用于服务器中，包括以下步骤：
201、该服务器识别图像的肤色区域，对该肤色区域中像素点的原始颜色数据进行统计，得到该肤色区域中像素点的原始均值和原始标准差。
其中，从图像来源上说，该图像可以为终端拍摄后上传至该服务器的图像，也可以为其他服务器发送给该服务器的图像，从图像内容上说，该图像包括肤色区域，具体可以包括人脸区域，或者包括人的全身区域等，本实施例对此不做限定。当终端拍摄到图像时，可以自动上传至该服务器，该服务器对该图像进行肤色调整后，发送给该终端，该终端直接显示调整后的图像，或者该终端显示拍摄的图像，当用户触发对该图像的肤色调整指令时，该终端再将该图像上传至该服务器，由该服务器对该图像进行肤色调整后，发送给该终端，该终端再显示调整后的图像。本实施例对此也不做
限定。
可选地，该服务器采用肤色检测算法对该图像进行识别，根据肤色检测算子，选定该图像的样本像素点，采用高斯混合模型，对肤色进行颜色建模，应用建立的颜色模型，对该图像中的肤色区域和非肤色区域进行分类，得到该图像的肤色区域。该服务器可能会识别出该图像的多个肤色区域，如人脸图像中的额头肤色区域、脸颊肤色区域和鼻翼肤色区域等，则该服务器对每个肤色区域分别进行肤色调整，本实施例仅以该图像的一个肤色区域为例进行说明。
在本实施例中，该服务器可以选取该肤色区域内的多个样本像素点，获取每个样本像素点的原始颜色数据，对该多个样本像素点的原始颜色数据进行统计，得到该多个样本像素点的原始颜色数据的均值和标准差，作为该肤色区域中像素点的原始均值和原始标准差。
以该原始颜色数据为YUV数据为例，该服务器获取到的原始均值为
原始标准差为
在YUV的三维空间中，该肤色区域的检测结果为一个椭球形，该原始均值为椭球形的球心，该原始标准差中的三个元素为该椭球形的三个球半径。
202、该服务器计算该原始均值与该至少一个预设肤色模型的预设均值之间的相似度，从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的相似度最大，确定该指定肤色模型的预设均值和预设标准差。
在本实施例中，为了提高肤色调整的准确性，该服务器预先建立该至少一个预设肤色模型，获取该至少一个预设肤色模型的预设均值和预设标准差。每个预设肤色模型用于表示一种肤色类型，该服务器根据该原始均值和该至少一个预设肤色模型的预设均值之间的相似度，可以确定与该肤色区域最相似的指定肤色类型，基于该指定肤色类型进行调整时，可以减小调整后的肤色与实际肤色的差距，避免图像出现失真。
相应的，在步骤202之前，该方法还包括：该服务器建立该至少一个预设肤色模型。具体地，该服务器选取不同肤色类型的样本图像，对于每一种肤色类型，该服务器对属于该肤色类型的多个样本图像的颜色数据进行训练统计和建模，得到该肤色类型对应的预设肤色模型，以及该预设肤色模型的均值和标准差，作为该预设肤色模型的预设均值和预设标准差。对每个样本图片进行统计的过程与该步骤201类似，在此不再赘述。在YUV的三维空间中，该预设肤色模型为一个椭球形，该预设均值为该椭球形的球心，该预设标准差中的三个元素为该椭球形的三个球半径。
进一步地，该服务器可以对多个样本图像的颜色数据进行离线统计，即在获取到该预设肤色模型的预设均值和预设标准差时，删除该样本图像的颜色数据，以节省存储空间。
其中，样本图像的选取要求为：样本图像中的肤色区域清晰且美观，以保证后续基于该指定肤色模型对该肤色区域进行肤色调整时，该调整后的肤色区域不仅不会出现失真，而且可以满足用户的美化需求。
可选地，将人类的肤色类型分为浅色白种人、深色白种人、浅色黄种人、深色黄种人、浅色黑种人、深色黑种人，该服务器根据属于上述六种肤色类型的样本图像分别进行统计，建立六个预设肤色模型：第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型。其中，该第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；该第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；该第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；该第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；该第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；该第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
在本实施例中，该服务器计算该原始均值与该至少一个预设肤色模型之间的相似度，相似度越大，表示该肤色区域与相应的预设肤色模型越相似，则该服务器从该至少一个预设肤色模型中选取预设均值与该原始均值之间的相似度最大的预设肤色模型，作为该指定肤色模型，该指定肤色模型即为与该肤色区域最相似的肤色模型。例如，当该肤色区域为浅色黄种人的肤色区域时，该服务器通过计算该原始均值与该至少一个预设均值之间的相似度，确定该第三预设肤色模型的预设均值与该原始均值之间的相似度最大，则将该第三预设肤色模型作为该指定肤色模型，基于该第三肤色模型对该肤色区域进行肤色调整。
可选地，该服务器计算该原始均值与该至少一个预设均值之间的欧式距离，欧式距离越小，表示该肤色区域与相应的预设肤色模型越相似，则从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的欧式距离最小。即应用以下公式确定该指定肤色模型：
其中，
为该原始均值，
为第i个预设肤色模型的预设均值，i＝1，2…n，n为预设肤色模型的数目，
为两个向量
和
之间的欧式距离，iType为该指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的欧式距离最小。
或者，该服务器计算该原始均值与该至少一个预设均值之间的余弦相似度，余弦相似度越大，表示该肤色区域与相应的预设肤色模型越相似，则从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的余弦相似度最大。本实施例对该相似度的类型不做限定。
在本实施例提供的另一实施例中，该服务器还可以计算该原始均值与该至少一个预设均值之间的差值，差值越小，表示该肤色区域与相应的预设肤色模型越相似，则从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的
差值最小。
203、该服务器根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据，根据该目标颜色数据，对该肤色区域进行调整。
可选地，该原始颜色数据为YUV数据，对于该肤色区域中的每个像素点，该服务器根据该像素点的原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，应用以下公式，确定该像素点的目标颜色数据：
其中，
为该像素点的原始颜色数据，Y为该原始颜色数据在YUV空间中维度Y上的取值，U为该原始颜色数据在YUV空间中维度U上的取值，V为该原始颜色数据在YUV空间中维度V上的取值；
为该像素点的目标颜色数据，Y*为该目标颜色数据在YUV空间中维度Y上的取值，U*为该目标颜色数据在YUV空间中维度U上的取值，V*为该目标颜色数据在YUV空间中维度V上的取值；
为该原始均值，meanY为该原始均值在YUV空间中维度Y上的取值，meanU为该原始均值在YUV空间中维度U上的取值，meanV为该原始均值在YUV空间中维度V上的取值；
为该原始标准差，deltaY为该原始标准差在YUV空间中维度Y上的取值，deltaU为该原始标准差在YUV空间中维度U上的取值，deltaV为该原始标准差在YUV空间中维度V上的取值；
为该指定肤色模型的预设均值，
为该预设均值在YUV空间中维度Y上的取值，meanUiType为该预设均值在YUV空间中维度U上的取值，meanViType为该预设均值在YUV空间中维度V上的取值；
为该指定肤色模型的预设标准差，deltaYiType为该预设标准差在YUV空间中维度Y上的取值，deltaUiType为该预设标准差在YUV空间中维度U上的取值，deltaViType为该预设标准差在YUV空间中维度V上的取值。
或者，该服务器可以根据上述公式，得到以下公式，并应用以下公式，确定该像素点的目标颜色数据：
该服务器确定该肤色区域中的每个像素点的目标颜色数据后，将每个像素点的原始颜色数据调整为对应的目标颜色数据，实现了肤色调整。
本实施例通过对该肤色区域中像素点的原始颜色数据进行统计，并根据肤色模型的相似性，从该至少一个预设肤色模型中，智能地选取与该肤色区域最相似的指定肤色模型，基于该指定肤色模型进行肤色调整，减小了调整后的肤色与实际肤色的差距，避免图像出现失真，算法简单，易于实现。
需要说明的是，本实施例以执行主体为该服务器为例进行说明，而实际上，执行主体还可以为终端，该终端下载该服务器建立的至少一个预设肤色模型的预设均值和预设标准差，当该终端拍摄到图像时，应用本实施例提供的方法，对该图像的肤色区域进行肤色调整，本实施例对执行主体不做限定。
本实施例提供的方法，通过对肤色区域中像素点的原始颜色数据进行统计后选取与该肤色区域最相似的指定肤色模型，根据该原始颜色数据、原始均值和原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据，根据该目标颜色数据对该肤色区域进行调整。在该指定肤色模型的基础上对肤色区域进行调整时，减小了调整后的肤色与实际肤色的差距，避免图像出现失真，提高美化效果，无需用户选择目标颜色，操作简便，且算法简单，易于实现。
图3是根据一示例性实施例示出的一种肤色调整装置的框图。参照图3，该装置包括肤色区域识别模块301，统计模块302、肤色模型指定模块303、目标颜色确定模块304和肤色调整模块305。
该肤色区域识别模块301被配置为用于识别图像的肤色区域；
该统计模块302被配置为用于对该肤色区域中像素点的原始颜色数据进行统计，得到该肤色区域中像素点的原始均值和原始标准差；
该肤色模型指定模块303被配置为用于根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型，该预设肤色模型用于表示肤色类型；
该目标颜色确定模块304被配置为用于根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据；
该肤色调整模块305被配置为用于根据该目标颜色数据，对该肤色区域进行调整。
可选的，该肤色模型指定模块303包括：
相似度计算单元，用于计算该原始均值与该至少一个预设肤色模型的预设均值之间的
差值；
肤色模型选取单元，用于从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的差值最小。
可选的，该肤色模型指定模块303包括：
欧式距离计算单元，用于计算该原始均值与该至少一个预设均值之间的欧式距离；
该肤色模型选取单元，还用于从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的欧式距离最小。
可选的，该颜色数据为YUV数据，该目标颜色确定模块304，用于对于该肤色区域中的每个像素点，根据该像素点的原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，应用以下公式，确定该像素点的目标颜色数据：
其中，
为该像素点的原始颜色数据，Y为该原始颜色数据在YUV空间中维度Y上的取值，U为该原始颜色数据在YUV空间中维度U上的取值，V为该原始颜色数据在YUV空间中维度V上的取值；
可选的，该肤色调整模块305包括：
肤色调整单元，用于将该肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
可选的，该装置还包括：
肤色类型预设模块，用于设定该至少一个预设肤色类型，该至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；
该第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；
该第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；
该第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；
该第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；
该第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；
该第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
上述所有可选技术方案，可以采用任意结合形成本发明的可选实施例，在此不再一一赘述。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
需要说明的是：上述实施例提供的肤色调整装置在调整肤色时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将服务器的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的肤色调整装置与肤色调整方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
图4是根据一示例性实施例示出的一种用于肤色调整的装置400的框图。例如，装置400可以被提供为一服务器。参照图4，装置400包括处理组件422，其进一步包括一个或多个处理器，以及由存储器432所代表的存储器资源，用于存储可由处理部件422的执行的指令，例如应用程序。存储器432中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件422被配置为执行指令，
以执行上述肤色调整方法。
装置400还可以包括一个电源组件426被配置为执行装置400的电源管理，一个有线或无线网络接口450被配置为将装置400连接到网络，和一个输入输出(I/O)接口458。装置400可以操作基于存储在存储器432的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
图5是根据一示例性实施例示出的另一种用于肤色调整的装置500的框图。例如，装置500可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图5，装置500可以包括以下一个或多个组件：处理组件502，存储器504，电源组件506，多媒体组件508，音频组件510，输入/输出(I/O)的接口512，传感器组件514，以及通信组件516。
处理组件502通常控制装置500的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理元件502可以包括一个或多个处理器520来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件502可以包括一个或多个模块，便于处理组件502和其他组件之间的交互。例如，处理部件502可以包括多媒体模块，以方便多媒体组件508和处理组件502之间的交互。
存储器504被配置为存储各种类型的数据以支持在设备500的操作。这些数据的示例包括用于在装置500上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器504可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电力组件506为装置500的各种组件提供电力。电力组件506可以包括电源管理系统，一个或多个电源，及其他与为装置500生成、管理和分配电力相关联的组件。
多媒体组件508包括在所述装置500和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件508包括一个前置摄像头和/或后置摄像头。当设备500处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件510被配置为输出和/或输入音频信号。例如，音频组件510包括一个
麦克风(MIC)，当装置500处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器504或经由通信组件516发送。在一些实施例中，音频组件510还包括一个扬声器，用于输出音频信号。
I/O接口512为处理组件502和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件514包括一个或多个传感器，用于为装置500提供各个方面的状态评估。例如，传感器组件514可以检测到设备500的打开/关闭状态，组件的相对定位，例如所述组件为装置500的显示器和小键盘，传感器组件514还可以检测装置500或装置500一个组件的位置改变，用户与装置500接触的存在或不存在，装置500方位或加速/减速和装置500的温度变化。传感器组件514可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件514还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件514还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件516被配置为便于装置500和其他设备之间有线或无线方式的通信。装置500可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信部件516经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，该通信部件516还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置500可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器504，上述指令可由装置500的处理器520执行以完成上述方法。例如，该非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
一种非临时性计算机可读存储介质，当该存储介质中的指令由移动终端的处理器执行时，使得移动终端能够执行一种肤色调整方法，该方法包括：
识别图像的肤色区域；
对该肤色区域中像素点的原始颜色数据进行统计，得到该肤色区域中像素点的原始均
值和原始标准差；
根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型，该预设肤色模型用于表示肤色类型；
根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据；
根据该目标颜色数据，对该肤色区域进行调整。
可选的，该根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型包括：
计算该原始均值与该至少一个预设肤色模型的预设均值之间的差值；
从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的差值最小。
可选的，该根据该原始均值和至少一个预设肤色模型的预设均值，从该至少一个预设肤色模型中选取与该肤色区域最相似的指定肤色模型包括：
计算该原始均值与该至少一个预设均值之间的欧式距离；
从该至少一个预设肤色模型中选取指定肤色模型，该指定肤色模型的预设均值与该原始均值之间的欧式距离最小。
可选的，该颜色数据为YUV数据，该根据该原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，确定目标颜色数据包括：
对于该肤色区域中的每个像素点，根据该像素点的原始颜色数据、该原始均值和该原始标准差、该指定肤色模型的预设均值和预设标准差，应用以下公式，确定该像素点的目标颜色数据：
其中，
为该像素点的原始颜色数据，Y为该原始颜色数据在YUV空间中维度Y上的取值，U为该原始颜色数据在YUV空间中维度U上的取值，V为该原始颜色数据在YUV空间中维度V上的取值；
可选的，该根据该目标颜色数据，对该肤色区域进行调整包括：
将该肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
可选的，该至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；
该第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；
该第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；
该第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；
该第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；
该第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；
该第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
上述所有可选技术方案，可以采用任意结合形成本发明的可选实施例，在此不再一一赘述。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本发明的其它实施方案。本申请旨在涵盖本发明的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本发明的真正范围和精神由下面的权利要求指出。
应当理解的是，本发明并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本发明的范围仅由所附的权利要求来限制。
Claims (13)
- 一种肤色调整方法，其特征在于，所述方法包括：识别图像的肤色区域；对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；根据所述目标颜色数据，对所述肤色区域进行调整。
- 根据权利要求1所述的方法，其特征在于，所述根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型包括：计算所述原始均值与所述至少一个预设肤色模型的预设均值之间的差值；从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的差值最小。
- 根据权利要求1所述的方法，其特征在于，所述根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型包括：计算所述原始均值与所述至少一个预设均值之间的欧式距离；从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的欧式距离最小。
- 根据权利要求1所述的方法，其特征在于，所述颜色数据为YUV数据，所述根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据包括：对于所述肤色区域中的每个像素点，根据所述像素点的原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，应用以下公式，确定所述像素点的目标颜色数据：
其中，为所述像素点的原始颜色数据，Y为所述原始颜色数据在YUV空间中维度Y上的取值，U为所述原始颜色数据在YUV空间中维度U上的取值，V为所述原始颜色数据在YUV空间中维度V上的取值；
为所述像素点的目标颜色数据，Y*为所述目标颜色数据在YUV空间中维度Y上的取值，U*为所述目标颜色数据在YUV空间中维度U上的取值，V*为所述目标颜色数据在YUV空间中维度V上的取值；
为所述原始均值，meanY为所述原始均值在YUV空间中维度Y上的取值，meanU为所述原始均值在YUV空间中维度U上的取值，meanV为所述原始均值在YUV空间中维度V上的取值；
为所述原始标准差，deltaY为所述原始标准差在YUV空间中维度Y上的取值，deltaU为所述原始标准差在YUV空间中维度U上的取值，deltaV为所述原始标准差在YUV空间中维度V上的取值；
为所述指定肤色模型的预设均值，meanYiType为所述预设均值在YUV空间中维度Y上的取值，meanUiType为所述预设均值在YUV空间中维度U上的取值，meanViType为所述预设均值在YUV空间中维度V上的取值；
为所述指定肤色模型的预设标准差，deltaYiType为所述预设标准差在YUV空间中维度Y上的取值，deltaUiType为所述预设标准差在YUV空间中维度U上的取值，deltaViType为所述预设标准差在YUV空间中维度V上的取值。
- 根据权利要求4所述的方法，其特征在于，所述根据所述目标颜色数据，对所述肤色区域进行调整包括：将所述肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
- 根据权利要求1-5任一项所述的方法，其特征在于，所述至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；所述第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；所述第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；所述第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；所述第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数 据统计得到；所述第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；所述第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
- 一种肤色调整装置，其特征在于，所述装置包括：肤色区域识别模块，用于识别图像的肤色区域；统计模块，用于对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；肤色模型指定模块，用于根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；目标颜色确定模块，用于根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；肤色调整模块，用于根据所述目标颜色数据，对所述肤色区域进行调整。
- 根据权利要求7所述的装置，其特征在于，所述肤色模型指定模块包括：相似度计算单元，用于计算所述原始均值与所述至少一个预设肤色模型的预设均值之间的差值；肤色模型选取单元，用于从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的差值最小。
- 根据权利要求7所述的装置，其特征在于，所述肤色模型指定模块包括：欧式距离计算单元，用于计算所述原始均值与所述至少一个预设均值之间的欧式距离；所述肤色模型选取单元，还用于从所述至少一个预设肤色模型中选取指定肤色模型，所述指定肤色模型的预设均值与所述原始均值之间的欧式距离最小。
- 根据权利要求7所述的装置，其特征在于，所述装置采用YUV数据作为所述颜色数据；所述目标颜色确定模块，用于对于所述肤色区域中的每个像素点，根据所述像素点的原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，应用以下公式，确定所述像素点的目标颜色数据：
其中，为所述像素点的原始颜色数据，Y为所述原始颜色数据在YUV空间中维度Y上的取值，U为所述原始颜色数据在YUV空间中维度U上的取值，V为所述原始颜色数据在YUV空间中维度V上的取值；
为所述像素点的目标颜色数据，Y*为所述目标颜色数据在YUV空间中维度Y上的取值，U*为所述目标颜色数据在YUV空间中维度U上的取值，V*为所述目标颜色数据在YUV空间中维度V上的取值；
为所述原始均值，meanY为所述原始均值在YUV空间中维度Y上的取值，meanU为所述原始均值在YUV空间中维度U上的取值，meanV为所述原始均值在YUV空间中维度V上的取值；
为所述原始标准差，deltaY为所述原始标准差在YUV空间中维度Y上的取值，deltaU为所述原始标准差在YUV空间中维度U上的取值，deltaV为所述原始标准差在YUV空间中维度V上的取值；
为所述指定肤色模型的预设均值，meanYiType为所述预设均值在YUV空间中维度Y上的取值，meanUiType为所述预设均值在YUV空间中维度U上的取值，meanViType为所述预设均值在YUV空间中维度V上的取值；
为所述指定肤色模型的预设标准差，deltaYiType为所述预设标准差在YUV空间中维度Y上的取值，deltaUiType为所述预设标准差在YUV空间中维度U上的取值，deltaViType为所述预设标准差在YUV空间中维度V上的取值。
- 根据权利要求10所述的装置，其特征在于，所述肤色调整模块包括：肤色调整单元，用于将所述肤色区域中每个像素点的原始颜色数据调整为每个像素点的目标颜色数据。
- 根据权利要求7-11任一项所述的装置，其特征在于，所述装置还包括：肤色模型预设模块，用于设定所述至少一个预设肤色模型，所述至少一个预设肤色模型包括第一预设肤色模型、第二预设肤色模型、第三预设肤色模型、第四预设肤色模型、第五预设肤色模型和第六预设肤色模型；所述第一预设肤色模型的预设均值和预设标准差根据浅色白种人样本图像的颜色数据统计得到；所述第二预设肤色模型的预设均值和预设标准差根据深色白种人样本图像的颜色数据统计得到；所述第三预设肤色模型的预设均值和预设标准差根据浅色黄种人样本图像的颜色数据统计得到；所述第四预设肤色模型的预设均值和预设标准差根据深色黄种人样本图像的颜色数据统计得到；所述第五预设肤色模型的预设均值和预设标准差根据浅色黑种人样本图像的颜色数据统计得到；所述第六预设肤色模型的预设均值和预设标准差根据深色黑种人样本图像的颜色数据统计得到。
- 一种肤色调整装置，其特征在于，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为：识别图像的肤色区域；对所述肤色区域中像素点的原始颜色数据进行统计，得到所述肤色区域中像素点的原始均值和原始标准差；根据所述原始均值和至少一个预设肤色模型的预设均值，从所述至少一个预设肤色模型中选取与所述肤色区域最相似的指定肤色模型，所述预设肤色模型用于表示肤色类型；根据所述原始颜色数据、所述原始均值和所述原始标准差、所述指定肤色模型的预设均值和预设标准差，确定目标颜色数据；根据所述目标颜色数据，对所述肤色区域进行调整。
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020157001233A KR101649596B1 (ko) | 2014-07-23 | 2014-11-19 | 피부색 조절방법, 장치, 프로그램 및 기록매체 |
| RU2015105702/07A RU2578210C1 (ru) | 2014-07-23 | 2014-11-19 | Способ и устройство для корректировки цвета кожи |
| JP2016535338A JP2016531362A (ja) | 2014-07-23 | 2014-11-19 | 肌色調整方法、肌色調整装置、プログラム及び記録媒体 |
| MX2015002145A MX352362B (es) | 2014-07-23 | 2014-11-19 | Metodo y dispositivo para ajustar el color de piel. |
| BR112015003977A BR112015003977A2 (pt) | 2014-07-23 | 2014-11-19 | método e dispositivo de ajuste da cor da pele |
| US14/666,479 US20160027191A1 (en) | 2014-07-23 | 2015-03-24 | Method and device for adjusting skin color |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410351282.XA CN104156915A (zh) | 2014-07-23 | 2014-07-23 | 肤色调整方法和装置 |
| CN201410351282.X | 2014-07-23 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US14/666,479 Continuation US20160027191A1 (en) | 2014-07-23 | 2015-03-24 | Method and device for adjusting skin color |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016011747A1 true WO2016011747A1 (zh) | 2016-01-28 |
Family
ID=51882406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2014/091652 WO2016011747A1 (zh) | 2014-07-23 | 2014-11-19 | 肤色调整方法和装置 |
Country Status (9)
| Country | Link |
|---|---|
| US (1) | US20160027191A1 (zh) |
| EP (1) | EP2977959B1 (zh) |
| JP (1) | JP2016531362A (zh) |
| KR (1) | KR101649596B1 (zh) |
| CN (1) | CN104156915A (zh) |
| BR (1) | BR112015003977A2 (zh) |
| MX (1) | MX352362B (zh) |
| RU (1) | RU2578210C1 (zh) |
| WO (1) | WO2016011747A1 (zh) |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408702B (zh) * | 2014-12-03 | 2018-11-23 | 浩云星空信息技术（北京）有限公司 | 一种图像处理方法及装置 |
| CN104881853B (zh) * | 2015-05-28 | 2018-10-16 | 厦门美图之家科技有限公司 | 一种基于色彩概念化的肤色矫正方法和系统 |
| TW201705040A (zh) * | 2015-07-17 | 2017-02-01 | Tair Jiuh Enterprise Co Ltd | 基於人臉影像的人臉膚色的偵測與資料庫建立方法 |
| JP6041957B1 (ja) * | 2015-10-01 | 2016-12-14 | 株式会社日立製作所 | 超音波診断装置 |
| CN106611429B (zh) | 2015-10-26 | 2019-02-05 | 腾讯科技（深圳）有限公司 | 检测皮肤区域的方法和检测皮肤区域的装置 |
| CN105872760A (zh) * | 2015-12-02 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | 一种视频播放监测方法及装置 |
| US20170178287A1 (en) * | 2015-12-21 | 2017-06-22 | Glen J. Anderson | Identity obfuscation |
| CN105913373B (zh) * | 2016-04-05 | 2019-06-04 | Oppo广东移动通信有限公司 | 图像处理方法和装置 |
| CN106060402A (zh) * | 2016-07-06 | 2016-10-26 | 北京奇虎科技有限公司 | 一种图像数据的处理方法、装置和移动终端 |
| CN107038715B (zh) * | 2017-03-21 | 2022-03-08 | 腾讯科技（深圳）有限公司 | 一种图像处理方法及装置 |
| CN107231505B (zh) * | 2017-07-18 | 2019-09-10 | 北京小米移动软件有限公司 | 图像处理方法及装置 |
| CN107633252B (zh) * | 2017-09-19 | 2020-04-21 | 广州市百果园信息技术有限公司 | 肤色检测方法、装置及存储介质 |
| CN107680096A (zh) * | 2017-10-30 | 2018-02-09 | 北京小米移动软件有限公司 | 图像处理方法及装置 |
| CN107862657A (zh) * | 2017-10-31 | 2018-03-30 | 广东欧珀移动通信有限公司 | 图像处理方法、装置、计算机设备及计算机可读存储介质 |
| WO2019100282A1 (zh) * | 2017-11-23 | 2019-05-31 | 深圳和而泰智能控制股份有限公司 | 一种人脸肤色识别方法、装置和智能终端 |
| CN108021881B (zh) * | 2017-12-01 | 2023-09-01 | 腾讯数码（天津）有限公司 | 一种肤色分割方法、装置和存储介质 |
| CN108053452B (zh) * | 2017-12-08 | 2020-03-31 | 浙江理工大学 | 一种基于混合模型的数字图像色彩提取方法 |
| WO2019185852A2 (en) | 2018-03-30 | 2019-10-03 | Movidius Ltd. | Methods, systems, articles of manufacture and apparatus to generate digital scenes |
| CN108898587A (zh) * | 2018-06-19 | 2018-11-27 | Oppo广东移动通信有限公司 | 图片处理方法、图片处理装置及终端设备 |
| CN108898169B (zh) * | 2018-06-19 | 2021-06-01 | Oppo广东移动通信有限公司 | 图片处理方法、图片处理装置及终端设备 |
| CN108961157B (zh) * | 2018-06-19 | 2021-06-01 | Oppo广东移动通信有限公司 | 图片处理方法、图片处理装置及终端设备 |
| CN109377531A (zh) * | 2018-09-29 | 2019-02-22 | 努比亚技术有限公司 | 图像偏色调整方法、装置、移动终端及可读存储介质 |
| CN111047517B (zh) * | 2018-10-11 | 2022-09-30 | 展讯通信（上海）有限公司 | 肤色调节方法及装置、可读存储介质 |
| CN111091106B (zh) * | 2019-12-23 | 2023-10-10 | 浙江大华技术股份有限公司 | 图像聚类方法及装置、存储介质、电子装置 |
| CN111476849B (zh) * | 2020-04-03 | 2023-08-29 | 腾讯科技（深圳）有限公司 | 对象颜色识别方法、装置、电子设备以及存储介质 |
| CN111627076B (zh) * | 2020-04-28 | 2023-09-19 | 广州方硅信息技术有限公司 | 换脸方法、装置及电子设备 |
| CN113822806B (zh) * | 2020-06-19 | 2023-10-03 | 北京达佳互联信息技术有限公司 | 图像处理方法、装置、电子设备和存储介质 |
| CN111831193A (zh) * | 2020-07-27 | 2020-10-27 | 北京思特奇信息技术股份有限公司 | 自动换肤方法、装置、电子设备及存储介质 |
| CN113837928A (zh) * | 2021-09-17 | 2021-12-24 | 平安普惠企业管理有限公司 | 对象颜色调整方法、装置、电子设备及存储介质 |
| WO2024077379A1 (en) * | 2022-10-11 | 2024-04-18 | Fitskin Inc. | Systems and methods for improved skin tone rendering in digital images |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280121B2 (en) * | 2008-12-31 | 2012-10-02 | Altek Corporation | Method of establishing skin color model |
| CN103065290A (zh) * | 2013-01-23 | 2013-04-24 | 广东欧珀移动通信有限公司 | 在照片中进行肤色校正的装置和方法 |
| CN103325089A (zh) * | 2012-03-21 | 2013-09-25 | 腾讯科技（深圳）有限公司 | 图像中的肤色处理方法及装置 |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003299115A (ja) | 2002-03-29 | 2003-10-17 | Fuji Photo Film Co Ltd | 画像信号処理装置 |
| KR100543698B1 (ko) * | 2002-12-14 | 2006-01-20 | 삼성전자주식회사 | 영상신호의 피부색 재현 장치 및 방법 |
| JP4277534B2 (ja) | 2003-02-12 | 2009-06-10 | オムロン株式会社 | 画像編集装置および画像編集方法 |
| EP1510973A3 (en) * | 2003-08-29 | 2006-08-16 | Samsung Electronics Co., Ltd. | Method and apparatus for image-based photorealistic 3D face modeling |
| WO2005057908A1 (ja) * | 2003-12-11 | 2005-06-23 | Fujitsu Limited | 画像処理方法及びプログラム、並びに装置 |
| JP2006279460A (ja) * | 2005-03-29 | 2006-10-12 | Seiko Epson Corp | 画像処理装置、印刷装置、画像処理方法、および、画像処理プログラム |
| JP2007257087A (ja) * | 2006-03-20 | 2007-10-04 | Univ Of Electro-Communications | 肌色領域検出装置及び肌色領域検出方法 |
| US8175382B2 (en) * | 2007-05-10 | 2012-05-08 | Microsoft Corporation | Learning image enhancement |
| WO2010062284A1 (en) * | 2008-11-25 | 2010-06-03 | Hewlett-Packard Development Company, L.P. | Modification of memory colors in digital images |
| US8265410B1 (en) * | 2009-07-11 | 2012-09-11 | Luxand, Inc. | Automatic correction and enhancement of facial images |
| US8406519B1 (en) * | 2010-03-10 | 2013-03-26 | Hewlett-Packard Development Company, L.P. | Compositing head regions into target images |
| KR101743520B1 (ko) * | 2011-04-09 | 2017-06-08 | 에스프린팅솔루션 주식회사 | 색상 변환 장치 및 그 방법 |
-
2014
- 2014-07-23 CN CN201410351282.XA patent/CN104156915A/zh active Pending
- 2014-11-19 WO PCT/CN2014/091652 patent/WO2016011747A1/zh active Application Filing
- 2014-11-19 KR KR1020157001233A patent/KR101649596B1/ko active IP Right Grant
- 2014-11-19 MX MX2015002145A patent/MX352362B/es active IP Right Grant
- 2014-11-19 RU RU2015105702/07A patent/RU2578210C1/ru active
- 2014-11-19 BR BR112015003977A patent/BR112015003977A2/pt not_active IP Right Cessation
- 2014-11-19 JP JP2016535338A patent/JP2016531362A/ja active Pending
-
2015
- 2015-03-24 US US14/666,479 patent/US20160027191A1/en not_active Abandoned
- 2015-05-27 EP EP15169404.9A patent/EP2977959B1/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280121B2 (en) * | 2008-12-31 | 2012-10-02 | Altek Corporation | Method of establishing skin color model |
| CN103325089A (zh) * | 2012-03-21 | 2013-09-25 | 腾讯科技（深圳）有限公司 | 图像中的肤色处理方法及装置 |
| CN103065290A (zh) * | 2013-01-23 | 2013-04-24 | 广东欧珀移动通信有限公司 | 在照片中进行肤色校正的装置和方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2016531362A (ja) | 2016-10-06 |
| KR101649596B1 (ko) | 2016-08-19 |
| EP2977959A2 (en) | 2016-01-27 |
| RU2578210C1 (ru) | 2016-03-27 |
| MX352362B (es) | 2017-11-22 |
| CN104156915A (zh) | 2014-11-19 |
| EP2977959A3 (en) | 2016-08-03 |
| US20160027191A1 (en) | 2016-01-28 |
| EP2977959B1 (en) | 2019-03-20 |
| MX2015002145A (es) | 2016-03-15 |
| BR112015003977A2 (pt) | 2017-07-04 |
| KR20160021738A (ko) | 2016-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016011747A1 (zh) | 肤色调整方法和装置 | |
| US10565763B2 (en) | Method and camera device for processing image | |
| JP6134446B2 (ja) | 画像分割方法、画像分割装置、画像分割デバイス、プログラム及び記録媒体 | |
| CN109345485B (zh) | 一种图像增强方法、装置、电子设备及存储介质 | |
| CN106408603B (zh) | 拍摄方法及装置 | |
| WO2017016146A1 (zh) | 图像显示方法及装置 | |
| JP6335289B2 (ja) | 画像フィルタを生成する方法及び装置 | |
| EP3125547A1 (en) | Method and device for switching color gamut mode | |
| WO2017031901A1 (zh) | 人脸识别方法、装置及终端 | |
| WO2017092289A1 (zh) | 图像处理方法及装置 | |
| US11308692B2 (en) | Method and device for processing image, and storage medium | |
| WO2022077970A1 (zh) | 特效添加方法及装置 | |
| WO2022110837A1 (zh) | 图像处理方法及装置 | |
| CN107730448B (zh) | 基于图像处理的美颜方法及装置 | |
| CN107231505B (zh) | 图像处理方法及装置 | |
| RU2614541C2 (ru) | Способ, устройство и терминал для перенастройки изображения | |
| WO2020114097A1 (zh) | 一种边界框确定方法、装置、电子设备及存储介质 | |
| EP3211879A1 (en) | Method and device for automatically capturing photograph, electronic device | |
| WO2021189927A1 (zh) | 图像处理方法、装置、电子设备及存储介质 | |
| US9665925B2 (en) | Method and terminal device for retargeting images | |
| CN107239758B (zh) | 人脸关键点定位的方法及装置 | |
| US9619016B2 (en) | Method and device for displaying wallpaper image on screen | |
| CN114418865A (zh) | 图像处理方法、装置、设备及存储介质 | |
| CN107025638B (zh) | 图像处理的方法及装置 | |
| WO2023231009A1 (zh) | 一种对焦方法、装置及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 2016535338 Country of ref document: JP Kind code of ref document: A |
|
| ENP | Entry into the national phase |
Ref document number: 20157001233 Country of ref document: KR Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: MX/A/2015/002145 Country of ref document: MX |
|
| ENP | Entry into the national phase |
Ref document number: 2015105702 Country of ref document: RU Kind code of ref document: A |
|
| REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112015003977 Country of ref document: BR |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14897984 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 112015003977 Country of ref document: BR Kind code of ref document: A2 Effective date: 20150225 |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 14897984 Country of ref document: EP Kind code of ref document: A1 |