CN104881853B - A kind of colour of skin antidote and system based on color generalities - Google Patents
A kind of colour of skin antidote and system based on color generalities Download PDFInfo
- Publication number
- CN104881853B CN104881853B CN201510280619.7A CN201510280619A CN104881853B CN 104881853 B CN104881853 B CN 104881853B CN 201510280619 A CN201510280619 A CN 201510280619A CN 104881853 B CN104881853 B CN 104881853B
- Authority
- CN
- China
- Prior art keywords
- color
- skin
- colour
- human face
- face region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of colour of skin antidotes and system based on color generalities, it obtains human face region by carrying out recognition of face to pending image, and the human face region to recognizing carries out luminance evaluation, brightness enhancing processing further is carried out to pending image if assessment result is dark figure, then hue statistical is carried out to the pixel of the human face region using color generalities algorithm, and color Transfer Parameters are calculated according to hue statistical result, finally the original colour of skin of pending image is converted into using the color Transfer Parameters it is expected the colour of skin, obtain effect image；Effect is more preferable, more natural, more stable, and operational efficiency higher, can achieve the effect that real-time beauty, is suitble to apply to mobile phone, camera and either realizes real-time beauty or to functions such as image beauty in the scenes such as APP.
Description
Technical field
The present invention relates to technical field of image processing, especially a kind of colour of skin antidote based on color generalities and its
Using the system of this method.
Background technology
In recent years, with the rapid development of electronic product, mobile phone, which has been not content with, only is used as communication tool, present
Intelligent machine, which already combines, functions and the whole body such as communicates, is social, entertaining, learn and take pictures.Especially camera function is constantly forced
Nearly camera is horizontal, and then self-timer is at vast electronic product user --- activity especially common in female life.In order to carry
High self-timer effect allows people to take more beautiful photo, and various image beauty algorithms come into being, and many Internet enterprises
It is dedicated to researching and developing the APP of various image beauty, user is supplied to use.
The algorithm of color generalities (Color Conceptualization) is expanding and extending for color pass-algorithm.
Wherein, " generalities " refer to several tone distributed models by being extracted after being clustered to great amount of images, color generalities
It is the adjustment of the tone distribution to input picture, so that it is distributed with similar tone with specified template image, to have
Have identical atmosphere, if but traditional color generalities algorithm directly apply to image beauty, be especially applied to the colour of skin correction,
The incoherent problem of color is easy tod produce, the integral color of the colour of skin and image is caused to be separated so that the image after beautification generates
The effect of distortion.
Invention content
The present invention is led to solve the above problems, provide a kind of colour of skin antidote and system based on color generalities
It crosses and pretreatment and improvement processing is carried out to traditional color generalities algorithm so that the effect after colour of skin correction is more natural.
To achieve the above object, the technical solution adopted by the present invention is：
A kind of colour of skin antidote based on color generalities, which is characterized in that include the following steps：
10. a pair pending image carries out recognition of face, human face region is obtained；
20. pair human face region recognized carries out luminance evaluation；
30. judging whether pending image is secretly to scheme according to luminance evaluation result, if dark figure is then further to pending
Image carries out brightness enhancing processing；
40. carrying out hue statistical to the pixel of the human face region using color generalities algorithm, and according to tone
Statistical result calculates color Transfer Parameters；
50. the human face region described in pair carries out skin color model, the original colour of skin is obtained, the color Transfer Parameters are recycled
The original colour of skin is converted into it is expected the colour of skin, obtains effect image.
Preferably, recognition of face is carried out to pending image in the step 10 and obtains human face region, mainly passed through
The positioning of face characteristic obtains the approximate region position of face, and obtains surrounding the rectangle frame of face as pending face area
Domain.
Preferably, luminance evaluation is carried out to the human face region recognized in the step 20, mainly using traversal
Mode accesses each pixel of the human face region, and counts the number of the pixel in each gray level, to count
Calculation obtains the grey level histogram of human face region, then from each single item of 0 to 127 cumulative histogram, and calculates cumulative rear histogram
Total grey scale pixel value with it is cumulative before histogram total grey scale pixel value ratio, ratio is more than 0.5, then explanation is secretly to scheme, instead
Be not then secretly to scheme.
Preferably, brightness enhancing processing is carried out to pending image in the step 30, mainly uses following enhancing
One or more kinds of combinations in processing method：Histogram equalization, Retinex enhancings or Poisson's equation enhancing.
Preferably, color is carried out to the pixel of the human face region using color generalities algorithm in the step 40
Statistics is adjusted, the color value of the pixel of the human face region is mainly converted into HSV color spaces from rgb color space,
And statistics with histogram is carried out to the color value in the channels H of each pixel, obtain hue histogram.
Preferably, color Transfer Parameters are calculated according to hue statistical result in described 40, mainly utilized described
Hue histogram calculates its accumulation and function, and is obtained in Gaussian function come fitted Gaussian distribution using accumulation and function
Mean value and variance, using the mean value and variance as color Transfer Parameters.
Preferably, the original colour of skin is converted into it is expected using the color Transfer Parameters in the step 50
The colour of skin is right by calculated original colour of skin institute in step 40 mainly by the default mean value and variance it is expected corresponding to the colour of skin
The mean value and variance in the channels H answered replace with the mean value and variance corresponding to the preset expectation colour of skin, then by the face area
The color value of the pixel in domain is converted to rgb color space from HSV color spaces, obtains effect image.
In addition, the present invention also provides a kind of colour of skin correction systems based on color generalities, which is characterized in that it is wrapped
It includes：
Face recognition module carries out recognition of face to pending image, obtains human face region；
Luminance evaluation module carries out luminance evaluation to the human face region recognized；
Luminance enhancement module, when judging pending image according to luminance evaluation result for dark figure further to pending
Image carries out brightness enhancing processing；
Color generalities module carries out tone system using color generalities algorithm to the pixel of the human face region
Meter, and color Transfer Parameters are calculated according to hue statistical result；
Colour of skin rectification module carries out skin color model to the human face region, obtains the original colour of skin, recycle described
The original colour of skin is converted into it is expected the colour of skin by color Transfer Parameters, obtains effect image.
The beneficial effects of the invention are as follows：
A kind of colour of skin antidote and system based on color generalities of the present invention, by being carried out to pending image
Recognition of face obtains human face region, and the human face region to recognizing carries out luminance evaluation, into one if assessment result is dark figure
Step carries out brightness enhancing processing to pending image, then utilizes pixel of the color generalities algorithm to the human face region
Hue statistical is carried out, and color Transfer Parameters are calculated according to hue statistical result, finally utilizes the color Transfer Parameters
The original colour of skin of pending image is converted into it is expected the colour of skin, obtains effect image；The present invention is by carrying out pending image
Pretreatment carries out brightness enhancing to the dark figure under dim light so that the effect after colour of skin correction matches with ambient brightness effect, makes
Image is more natural；Colour of skin correction is carried out by the algorithm of color generalities, effect is more preferably more stable, and overcomes traditional colour of skin
The limitation of the linear transformation of beauty algorithm is converted to the colour of skin from any one tone by color generalities algorithm preset
It is expected that tone, operational efficiency higher can achieve the effect that real-time beauty, it is suitble to apply to the scenes such as mobile phone, camera or APP
In, to realize real-time beauty or to functions such as image beauty.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and constitutes the part of the present invention, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of general flow chart of the colour of skin antidote based on color generalities of the present invention；
Fig. 2 is a kind of structural schematic diagram of the colour of skin correction system based on color generalities of the present invention.
Specific implementation mode
In order to keep technical problems, technical solutions and advantages to be solved clearer, clear, tie below
Closing accompanying drawings and embodiments, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
As shown in Figure 1, a kind of colour of skin antidote based on color generalities of the present invention comprising following steps：
10. a pair pending image carries out recognition of face, human face region is obtained；
20. pair human face region recognized carries out luminance evaluation；
30. judging whether pending image is secretly to scheme according to luminance evaluation result, if dark figure is then further to pending
Image carries out brightness enhancing processing；
40. carrying out hue statistical to the pixel of the human face region using color generalities algorithm, and according to tone
Statistical result calculates color Transfer Parameters；
50. the human face region described in pair carries out skin color model, the original colour of skin is obtained, the color Transfer Parameters are recycled
The original colour of skin is converted into it is expected the colour of skin, obtains effect image.
Recognition of face is carried out to pending image in the step 10 and obtains human face region, mainly passes through face characteristic
Positioning obtain face approximate region position, and obtain surround face rectangle frame as pending human face region；Wherein
The algorithm of recognition of face mainly uses the prior art, for example, the recognizer based on human face characteristic point, is based on whole picture facial image
Recognizer, the recognizer based on template, the algorithm, etc. being identified using neural network, here without repeating.
Luminance evaluation is carried out to the human face region recognized in the step 20, traversal is mainly used in the present embodiment
Mode access each pixel of the human face region, and count the number of the pixel in each gray level, to
The grey level histogram of human face region is calculated, then from each single item of 0 to 127 cumulative histogram, and calculates cumulative rear histogram
The ratio of total grey scale pixel value of figure and total grey scale pixel value of cumulative preceding histogram, ratio are more than 0.5, then explanation is secretly to scheme,
It is on the contrary then be not secretly to scheme.
Brightness enhancing processing is carried out to pending image in the step 30, mainly uses following enhancing processing method
In one or more kinds of combinations：Histogram equalization, Retinex enhancings or Poisson's equation enhance, in the present embodiment preferably
For Retinex Enhancement Methods.
Hue statistical is carried out to the pixel of the human face region using color generalities algorithm in the step 40,
The color value of the pixel of the human face region is mainly converted into HSV color spaces from rgb color space, and to each
The color value in the channels H of pixel carries out statistics with histogram, obtains hue histogram；According to hue statistical result in described 40
Calculate color Transfer Parameters, mainly calculate its accumulation and function using the hue histogram, and using accumulation and
Function carrys out fitted Gaussian distribution, obtains the mean value in Gaussian function and variance, using the mean value and variance as color Transfer Parameters.
In the present embodiment, the calculation formula of hue statistical is as follows：
Wherein, H (p), S (p), V (p) are respectively the tone value of the pixel p in the human face region of pending image, saturation
Degree, brightness value；I is integer and i ∈ [1,360].
The original colour of skin is converted into the expectation colour of skin using the color Transfer Parameters in the step 50, it is main
If by the default mean value and variance it is expected corresponding to the colour of skin, the H corresponding to the calculated original colour of skin in step 40 is led to
The mean value and variance in road replace with the mean value and variance corresponding to the preset expectation colour of skin, then by the pixel of the human face region
The color value of point is converted to rgb color space from HSV color spaces, obtains effect image.
It should be noted that carrying out skin color model to the human face region in the step 50 obtains the original colour of skin,
It is not to need to execute in strict accordance with number of steps sequence, can also be executed in the step of any one before step 50, example
As directly carried out skin color model after obtaining human face region in step 10.
As shown in Fig. 2, the present invention also provides a kind of colour of skin correction systems based on color generalities comprising：
Face recognition module A carries out recognition of face to pending image, obtains human face region；
Luminance evaluation module B carries out luminance evaluation to the human face region recognized；
Luminance enhancement module C further treats place when judging pending image according to luminance evaluation result for dark figure
It manages image and carries out brightness enhancing processing；
Color generalities module D carries out tone using color generalities algorithm to the pixel of the human face region
Statistics, and color Transfer Parameters are calculated according to hue statistical result；
Colour of skin rectification module E carries out skin color model to the human face region, obtains the original colour of skin, described in recycling
Color Transfer Parameters by the original colour of skin be converted into it is expected the colour of skin, obtain effect image.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment weight
Point explanation is all difference from other examples, and the same or similar parts between the embodiments can be referred to each other.
For system class embodiment, since it is basically similar to the method embodiment, so description is fairly simple, related place ginseng
See the part explanation of embodiment of the method.Also, herein, the terms "include", "comprise" or its any other variant
It is intended to non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only
Those elements, but also include other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of person's equipment.In the absence of more restrictions, the element limited by sentence "including a ...", not
There is also other identical elements in the process, method, article or apparatus that includes the element for exclusion.In addition, this field
Those of ordinary skill is appreciated that realize that all or part of step of above-described embodiment can be completed by hardware, can also lead to
Program is crossed to instruct relevant hardware to complete, the program can be stored in a kind of computer readable storage medium, above-mentioned
The storage medium mentioned can be read-only memory, disk or CD etc..
The preferred embodiment of the present invention has shown and described in above description, it should be understood that the present invention is not limited to this paper institutes
The form of disclosure is not to be taken as excluding other embodiments, and can be used for other combinations, modifications, and environments, and energy
Enough in this paper invented the scope of the idea, modifications can be made through the above teachings or related fields of technology or knowledge.And people from this field
The modifications and changes that member is carried out do not depart from the spirit and scope of the present invention, then all should be in the protection of appended claims of the present invention
In range.
Claims (5)
1. a kind of colour of skin antidote based on color generalities, which is characterized in that include the following steps：
10. a pair pending image carries out recognition of face, human face region is obtained；
20. pair human face region recognized carries out luminance evaluation；
30. judging whether pending image is secretly to scheme according to luminance evaluation result, if dark figure is then further to pending image
Carry out brightness enhancing processing；
40. carrying out hue statistical to the pixel of the human face region using color generalities algorithm, and according to hue statistical
As a result color Transfer Parameters are calculated；That is, the color value of the pixel of the human face region is converted to from rgb color space
HSV color spaces, and statistics with histogram is carried out to the color value in the channels H of each pixel, obtain hue histogram；Using institute
The hue histogram stated calculates its accumulation and function, and obtains Gaussian function using accumulation and function come fitted Gaussian distribution
In mean value and variance, using the mean value and variance as color Transfer Parameters；
50. the human face region described in pair carries out skin color model, the original colour of skin is obtained, recycles the color Transfer Parameters by institute
The original colour of skin stated is converted into it is expected the colour of skin, obtains effect image；That is, it is expected the mean value corresponding to the colour of skin and side by default
The mean value in the channels H corresponding to the calculated original colour of skin in step 40 and variance are replaced with preset expectation colour of skin institute by difference
Corresponding mean value and variance, then the color value of the pixel of the human face region is converted into rgb color from HSV color spaces
Space obtains effect image.
2. a kind of colour of skin antidote based on color generalities according to claim 1, it is characterised in that：The step
Recognition of face is carried out to pending image in rapid 10 and obtains human face region, is that face is obtained substantially by the positioning of face characteristic
Regional location, and obtain surrounding the rectangle frame of face as pending human face region.
3. a kind of colour of skin antidote based on color generalities according to claim 1, it is characterised in that：The step
Luminance evaluation is carried out to the human face region recognized in rapid 20, is each for accessing the human face region by the way of traversal
Pixel, and the number of the pixel in each gray level is counted, to which the grey level histogram of human face region be calculated, so
Afterwards from each single item of 0 to 127 cumulative histogram, and calculate it is cumulative after histogram total grey scale pixel value with it is cumulative before histogram
The ratio of total grey scale pixel value, ratio are more than 0.5, then explanation is secretly to scheme, on the contrary then be not secretly to scheme.
4. a kind of colour of skin antidote based on color generalities according to claim 1, it is characterised in that：The step
Brightness enhancing processing is carried out to pending image in rapid 30, is using one or more kinds of in following enhancing processing method
Combination：Histogram equalization, Retinex enhancings or Poisson's equation enhancing.
5. a kind of colour of skin correction system based on color generalities, which is characterized in that it includes：
Face recognition module carries out recognition of face to pending image, obtains human face region；
Luminance evaluation module carries out luminance evaluation to the human face region recognized；
Luminance enhancement module, when judging pending image according to luminance evaluation result for dark figure further to pending image
Carry out brightness enhancing processing；
Color generalities module carries out hue statistical using color generalities algorithm to the pixel of the human face region,
And color Transfer Parameters are calculated according to hue statistical result；That is, by the color value of the pixel of the human face region from RGB
Color space is converted to HSV color spaces, and carries out statistics with histogram to the color value in the channels H of each pixel, obtains color
Adjust histogram；Its accumulation and function are calculated using the hue histogram, and using accumulation and function come fitted Gaussian point
Cloth obtains the mean value in Gaussian function and variance, using the mean value and variance as color Transfer Parameters；
Colour of skin rectification module carries out skin color model to the human face region, obtains the original colour of skin, recycle the color
The original colour of skin is converted into it is expected the colour of skin by Transfer Parameters, obtains effect image；That is, it is expected corresponding to the colour of skin by default
Mean value and variance, the mean value in the channels H corresponding to the calculated original colour of skin in step 40 and variance are replaced with preset
It is expected that the mean value corresponding to the colour of skin and variance, then the color value of the pixel of the human face region is turned from HSV color spaces
It is changed to rgb color space, obtains effect image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510280619.7A CN104881853B (en) | 2015-05-28 | 2015-05-28 | A kind of colour of skin antidote and system based on color generalities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510280619.7A CN104881853B (en) | 2015-05-28 | 2015-05-28 | A kind of colour of skin antidote and system based on color generalities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104881853A CN104881853A (en) | 2015-09-02 |
| CN104881853B true CN104881853B (en) | 2018-10-16 |
Family
ID=53949338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510280619.7A Active CN104881853B (en) | 2015-05-28 | 2015-05-28 | A kind of colour of skin antidote and system based on color generalities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104881853B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106454054B (en) | 2016-11-29 | 2019-03-19 | Oppo广东移动通信有限公司 | Control method, control device and electronic device |
| CN106504218B (en) * | 2016-11-29 | 2019-03-12 | Oppo广东移动通信有限公司 | Control method, control device and electronic device |
| CN106341670B (en) | 2016-11-29 | 2017-09-22 | 广东欧珀移动通信有限公司 | Control method, control device and electronic installation |
| CN106937049B (en) * | 2017-03-09 | 2020-11-27 | Oppo广东移动通信有限公司 | Depth-of-field-based portrait color processing method and device and electronic device |
| CN107180415B (en) * | 2017-03-30 | 2020-08-14 | 北京奇艺世纪科技有限公司 | Skin beautifying processing method and device in image |
| CN107945106B (en) * | 2017-11-30 | 2022-02-15 | Oppo广东移动通信有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN108021901A (en) * | 2017-12-18 | 2018-05-11 | 北京小米移动软件有限公司 | The method, apparatus and computer-readable recording medium of image procossing |
| CN110020990B (en) * | 2018-01-10 | 2023-11-07 | 中兴通讯股份有限公司 | Global skin beautifying method, device and equipment of mobile terminal and storage medium |
| CN108391112A (en) * | 2018-04-02 | 2018-08-10 | 深圳Tcl新技术有限公司 | A kind of method, system and storage medium promoting display image quality |
| CN108629329B (en) * | 2018-05-17 | 2021-04-23 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
| CN108961192B (en) * | 2018-07-19 | 2021-06-29 | Tcl华星光电技术有限公司 | Image color saturation enhancement method, computer storage medium and display device |
| CN109394268B (en) * | 2018-12-07 | 2021-05-11 | 刘志红 | Polyp harm degree mapping platform |
| CN111899182B (en) * | 2019-05-06 | 2024-04-05 | 浙江宇视科技有限公司 | Color enhancement method and device |
| CN110086997B (en) * | 2019-05-20 | 2021-07-20 | 北京百度网讯科技有限公司 | Face image exposure brightness compensation method and device |
| CN110381303B (en) * | 2019-05-31 | 2021-07-09 | 成都品果科技有限公司 | Portrait automatic exposure white balance correction method and system based on skin color statistics |
| CN110378324B (en) * | 2019-07-15 | 2023-01-03 | 易诚高科（大连）科技有限公司 | Quality dimension-based face recognition algorithm evaluation method |
| CN111047533B (en) * | 2019-12-10 | 2023-09-08 | 成都品果科技有限公司 | Beautifying method and device for face image |
| CN111275725B (en) * | 2020-03-18 | 2022-08-19 | 展讯通信（上海）有限公司 | Method and device for determining color temperature and tone of image, storage medium and terminal |
| CN111898535A (en) * | 2020-07-30 | 2020-11-06 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and storage medium |
| CN112801997B (en) * | 2021-02-05 | 2023-06-06 | 抖音视界有限公司 | Image enhancement quality evaluation method, device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448085A (en) * | 2008-12-26 | 2009-06-03 | 北京中星微电子有限公司 | Videography processing method and system supporting face detection |
| CN101605273A (en) * | 2009-07-23 | 2009-12-16 | 青岛海信数字多媒体技术国家重点实验室有限公司 | A kind of method of evaluating colour saturation quality and subsystem |
| CN102005046A (en) * | 2010-11-10 | 2011-04-06 | 新太科技股份有限公司 | Novel method for detecting image color cast by color saturation detecting technology |
| CN104156915A (en) * | 2014-07-23 | 2014-11-19 | 小米科技有限责任公司 | Skin color adjusting method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130004070A1 (en) * | 2011-06-28 | 2013-01-03 | Huanzhao Zeng | Skin Color Detection And Adjustment In An Image |
-
2015
- 2015-05-28 CN CN201510280619.7A patent/CN104881853B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448085A (en) * | 2008-12-26 | 2009-06-03 | 北京中星微电子有限公司 | Videography processing method and system supporting face detection |
| CN101605273A (en) * | 2009-07-23 | 2009-12-16 | 青岛海信数字多媒体技术国家重点实验室有限公司 | A kind of method of evaluating colour saturation quality and subsystem |
| CN102005046A (en) * | 2010-11-10 | 2011-04-06 | 新太科技股份有限公司 | Novel method for detecting image color cast by color saturation detecting technology |
| CN104156915A (en) * | 2014-07-23 | 2014-11-19 | 小米科技有限责任公司 | Skin color adjusting method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104881853A (en) | 2015-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104881853B (en) | A kind of colour of skin antidote and system based on color generalities | |
| Yue et al. | Contrast enhancement based on intrinsic image decomposition | |
| CN111344712B (en) | System and method for image de-identification | |
| CN103914699B (en) | A kind of method of the image enhaucament of the automatic lip gloss based on color space | |
| CN106504212A (en) | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement | |
| CN104182947B (en) | Low-illumination image enhancement method and system | |
| CN109447910A (en) | A kind of low-luminance color image enchancing method based on fuzzy theory | |
| CN107798661B (en) | Self-adaptive image enhancement method | |
| CN107545536A (en) | The image processing method and image processing system of a kind of intelligent terminal | |
| CN104978710A (en) | Method and device for identifying and adjusting human face luminance based on photographing | |
| CN106780375A (en) | A kind of image enchancing method under low-light (level) environment | |
| Berezhnoy et al. | Computer analysis of van Gogh’s complementary colours | |
| CN105809643B (en) | A kind of image enchancing method based on adaptive block channel extrusion | |
| CN109871845A (en) | Certificate image extracting method and terminal device | |
| CN104811684A (en) | Three-dimensional beautification method and device of image | |
| CN106326823A (en) | Method and system for acquiring head image in picture | |
| CN106067016B (en) | A kind of facial image eyeglass detection method and device | |
| CN108024105A (en) | Image color adjusting method, device, electronic equipment and storage medium | |
| CN107609603A (en) | A kind of image matching method of multiple color spaces difference fusion | |
| CN104008364A (en) | Face recognition method | |
| CN103366390A (en) | Terminal, image processing method and device thereof | |
| CN110287787A (en) | Image-recognizing method, device and computer readable storage medium | |
| CN109829868A (en) | A kind of lightweight deep learning model image defogging method, electronic equipment and medium | |
| CN108345867A (en) | Gesture identification method towards Intelligent household scene | |
| CN113240760A (en) | Image processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |