CN108596992B - Rapid real-time lip gloss makeup method - Google Patents
Rapid real-time lip gloss makeup method Download PDFInfo
- Publication number
- CN108596992B CN108596992B CN201711494691.5A CN201711494691A CN108596992B CN 108596992 B CN108596992 B CN 108596992B CN 201711494691 A CN201711494691 A CN 201711494691A CN 108596992 B CN108596992 B CN 108596992B
- Authority
- CN
- China
- Prior art keywords
- image
- lip
- pixel
- matrix
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000000694 effects Effects 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 28
- 238000010606 normalization Methods 0.000 claims description 10
- 238000002156 mixing Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 210000000697 sensory organ Anatomy 0.000 claims description 4
- 230000001815 facial effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 230000003321 amplification Effects 0.000 abstract description 4
- 238000003199 nucleic acid amplification method Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 abstract description 2
- 210000001508 eye Anatomy 0.000 abstract description 2
- 230000008439 repair process Effects 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000037303 wrinkles Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Images
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a rapid and real-time lip gloss makeup method, which reduces a Mask image, reduces the original size after Gaussian filtering, and shortens more time on the computational efficiency. The amplified Mask image has better feathering effect at the edge part, so that the Gaussian filter kernel can be set to be smaller when being set to ensure the execution efficiency, and meanwhile, the insufficient feathering repair is carried out after the amplification, thereby ensuring the realization of the effect. In order to improve the execution efficiency, the minimum bounding rectangle is used for carrying out the local calculation of the image, so that the original image is prevented from being traversed in the calculation process, and the redundant calculation time is saved. In the aspect of lip color change, multiplication operation is directly carried out on the lip color and the weight value in the RGB three channels, and the lip color is more visual and clear in the aspects of color adjustment and control. The color effect observed by human eyes can be more closely represented in practical representation by directly adjusting the values of the RGB channels.
Description
Technical Field
The invention relates to a rapid and real-time lip gloss makeup method.
Background
In the digital image makeup integration technology, processing on the lip gloss part is important. First, the lips of human faces are similar and different in shape, and second, the lips have ever-changing lip wrinkles, and in order to achieve a more real effect in the process of makeup treatment, the lip wrinkles need to be kept and smoothened in a balanced manner so as to achieve a more natural and real makeup effect.
Chinese patent application No. 201210100239.7 proposes a method for lip gloss makeup based on different lip morphological characteristics. In this method, correction information of lip form is provided by a lip form balance of lip form using an image plane of lip and a three-dimensional lip form analysis using a lip form classification map composed of coordinates generated by the lip form classification method and coordinates generated by the lip form classification method, and based on a result of the plane and three-dimensional lip form analysis.
The above method requires a complicated classification process and a balance calculation process for the lips, and it is difficult to have a good expression effect in a case where the light is complicated.
Chinese patent application No. 201410157583.9 proposes an image enhancement method of automatic lip gloss based on color space. In the method, five sense organs are used for positioning to obtain the outline of the lip, a probability graph of lip pixels is generated by calculating the distribution of a color space, and each pixel in the lip probability graph is automatically colored with the lip color according to the probability graph and the color selected by a filter.
The method utilizes key positioning points of five sense organs, and solves the lip gloss makeup problem under various light rays or complex environments. But because the probability map of lip pixels is calculated through color distribution every time, and there are a plurality of times of color space conversion and filtering processing (gaussian blur, linear blur, mean value blur, etc.) of the global image, the amount of calculation in the implementation process is increased undoubtedly. In current terminal equipment, especially with mobile devices (smart phones, tablet computers) and embedded experience terminals, there is still a great space for improving the calculation efficiency of the cpu, and in order to achieve the real-time makeup and make-up effect of each part of the face, the reduction and optimization of the speed and the calculation amount become the key points for realization.
Disclosure of Invention
The invention aims to provide a quick and real-time lip gloss makeup method, and the lip gloss makeup method can keep the original characteristics (lip line structure and the like) of the lip after makeup, and simultaneously achieve the lip gloss makeup effect with more realistic fitting.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a rapid and real-time lip gloss makeup method comprising the steps of:
1) carrying out face recognition on an original image, acquiring key points of facial five sense organs, and selecting feature key points belonging to a lip contour from the key points;
2) loading the original image in an integer RGB color space distribution, and performing normalization processing to ensure that the pixel values of the image are distributed between 0.0 and 1.0;
3) respectively obtaining fitting curves of upper and lower lip contours;
4) acquiring all pixel sets of the curve according to the curve in the step 3), namely the pixel sets of the upper and lower lip outlines;
5) respectively acquiring minimum bounding rectangles of the upper lip and the lower lip according to the characteristic points in the step 1), respectively traversing the minimum bounding rectangles of the upper lip and the lower lip, and judging pixel sets contained in the curve in the rectangles by using the pixel coordinate sets in the step 3), namely all pixel sets of the upper lip and the lower lip;
6) constructing an original image 1 according to the upper and lower lip pixel sets obtained in the step 4): a gray Mask image of 1 relationship, in which the pixel values in the upper and lower lips are 1.0 and the remaining pixel values are 0.0;
7) changing the size of Mask image, and reducing it in equal proportion;
8) performing Gaussian filtering fuzzy processing on the Mask image to enable the edge of the Mask image to achieve the feathering effect;
9) enlarging the Mask image processed in the step 8) to form 1: 1 in a proportional relationship;
10) performing image mixing processing on the original image subjected to normalization in the step 2), wherein the processing mode is one of a positive film bottom-folding mode, a soft light mode and a superposition mode;
11) step 10), carrying out matrix pixel-by-pixel multiplication on an image RGB three-channel matrix obtained after image mixing processing and a Mask image respectively to obtain a matrix image of upper and lower lips subjected to edge feathering;
12) separating the RGB channel image matrix obtained in the step 11), and multiplying the RGB channel image matrix pixel by pixel with the weight value of R, G, B three channels respectively to achieve the purpose of changing the lip gloss;
13) performing pixel-by-pixel multiplication on the Mask image after the inversion operation and the RGB three-channel matrix of the original image normalized in the step 2) to obtain an image matrix which is the same as the original image but has pixels in upper and lower lips of 0.0;
14) carrying out addition operation on the matrix obtained in the step 11) and the matrix obtained in the step 13), and multiplying the matrix by a transparency coefficient to obtain a result image of synthesis processing;
15) and (5) carrying out reduction processing on the result in the step 14) to obtain a final effect image.
The invention reduces Mask image, reduces original size after Gaussian filtering, and shortens more time on calculation efficiency. In addition, the amplified Mask image has better feathering effect at the edge part, so that the Gaussian filter kernel can be set to be smaller when being set to ensure the execution efficiency, and meanwhile, the insufficient feathering repair is carried out after amplification, thereby ensuring the realization of the effect.
In order to improve the execution efficiency, the minimum bounding rectangle is used for carrying out the local calculation (upper and lower lips) of the image, so that the original image is prevented from being traversed in the calculation process, and the redundant calculation time is saved.
In the aspect of lip color change, multiplication operation is directly carried out on the lip color and the weight value in the RGB three channels, and the lip color is more visual and clear in the aspects of color adjustment and control. The color effect observed by human eyes can be more closely represented in practical representation by directly adjusting the values of the RGB channels.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
Referring to fig. 1, a fast and real-time lip gloss makeup method mainly includes the following core steps:
1) the method comprises the steps of carrying out face recognition on an original image, obtaining key points of facial features, selecting feature key points belonging to a lip outline from the key points, and dividing the feature key points into an upper lip and a lower lip, wherein the number of the feature points of the upper lip and the lower lip is 11 and 11 respectively.
2) The original image is normalized (the original image is loaded in an integer RGB color space distribution), and linear normalization is mainly applied, wherein the purpose of normalization is to enable the pixel values of the image to be distributed between 0.0 and 1.0. The application formula is as follows:
C＝(A-MinValue)/(MaxValue-MinValue)
wherein MinValue value is 0.0, and MaxValue value is 255.0
3) Fitting curves of the upper and lower lip profiles were obtained using the Douglas-Puck algorithm (Douglas-Peucker algorithm), respectively.
4) Acquiring all pixel sets of the curve according to the curve in the step 3), namely the pixel sets of the upper and lower lip outlines.
5) Respectively obtaining the minimum bounding rectangles of the upper lip and the lower lip according to the characteristic points in the step 1), respectively traversing the minimum bounding rectangles of the upper lip and the lower lip, and judging pixel sets contained in the curve in the rectangles by using the pixel coordinate sets in the step 3), namely all pixel sets of the upper lip and the lower lip.
6) Constructing an original image 1 according to the upper and lower lip pixel sets obtained in the step 4): a gray (single channel) Mask (Mask) diagram of 1 relationship, in which the pixel values in the upper and lower lips are 1.0 (i.e., pure white), and the remaining pixel values are 0.0 (i.e., pure black).
7) The dimension of Mask image is changed and scaled down to matrix image with width and height not exceeding 200 px. The Mask map is reduced on the one hand to obtain higher computational efficiency in the next step of gaussian blur to improve the speed.
8) The Mask image is subjected to Gaussian filtering fuzzy processing, and the transformation of each pixel in the image is calculated mainly by adopting normal distribution. The gaussian filtering is mainly used to make the edges of the Mask image feathered. The formula is adopted as follows:
where r is the blur radius and σ is the standard deviation of the normal distribution.
9) Enlarging Mask image processed in step 8) to form 1: 1. Through the reduction in 7) and the amplification of the current step, on one hand, higher execution efficiency can be obtained in processing Gaussian filtering, and on the other hand, through the reduction and the amplification, a Mask (Mask) image can obtain a better feathering effect in the edge, so that a more vivid transition effect can be obtained in later-stage synthesis.
10) And 2) carrying out image mixing processing on the original image subjected to normalization in the step 2), wherein the processing mode adopts one of three modes of positive film bottom folding, soft light and superposition. The corresponding formula is as follows:
stacking the front sheets: c is A2
And (3) superposition: c is A2*α,A≤1/α
C＝1–(1-A)2*α,A>1/α
Softening the light: c is A2*α+A2*(1-2*A),A≤1/α
C ═ a (1-a) × α + √ a (2 × a-1), a >1/α where α ═ 255.0/128.0, a is the single pixel value in the original image. Note that: since the original image is normalized, the formula is different from the original calculation formula.
11) And step 10), carrying out matrix pixel-by-pixel multiplication on an image RGB three-channel matrix obtained after image mixing processing and a Mask image respectively. Since the pixel value of the inside of the upper and lower lips in the Mask image is 1.0 and the remaining pixels are 0.0, the matrix image of the upper and lower lips subjected to edge feathering is obtained after pixel-by-pixel multiplication (the pixel values except the upper and lower lips are 0.0, that is, pure black).
12) Separating the RGB channel image matrix obtained in the step 11), and multiplying the RGB channel image matrix by the R, G, B three-channel weight value pixel by pixel. The step mainly comprises the step of adjusting the colors of RGB three channels according to the weight value to achieve the purpose of changing the lip gloss.
13) And (3) after the Mask image is subjected to negation operation, multiplying the Mask image by the RGB three-channel matrix of the original image normalized in the step (2) pixel by pixel respectively to obtain an image matrix which is the same as the original image but has pixels of 0.0 (namely pure black) in the upper lip and the lower lip.
14) And adding the matrix obtained in the step 11) and the matrix obtained in the step 13), and multiplying the obtained matrix by a transparency coefficient to obtain a result image of the synthesis processing. The formula is as follows
C＝A*α+B*(1.0-α),α∈{0,1}
Where A is the resulting image matrix in 11), B is the resulting matrix in 12), and α is the transparency coefficient.
15) And (4) performing reduction processing (reducing the result into original integer pixel data) on the result in the step 14) to obtain a final effect image. The formula is as follows:
C＝A*(MaxValue-MinValue)+MinValue
wherein MinValue value is 0.0, and MaxValue value is 255.0
The mode for loading the original image is mainly an RGB mode, and the RGB color space is always used as the calculation reference. The normalization processing is carried out, so that the subsequent operation of various matrix data is facilitated.
To improve the efficiency of the upper and lower lips, only the smallest bounding rectangle is computed as in 5)6) and 10), instead of the original image. The definition mode of the minimum matrix is that the minimum x value and the minimum y value in the coordinate point set of the corresponding contour (the upper lip or the lower lip) are taken as the x value and the y value of the upper left corner point of the rectangle, and the maximum x value and the maximum y value in the coordinate point set of the corresponding coordinate point (the upper lip or the lower lip) are taken as the x value and the y value of the lower right corner coordinate of the rectangle. Since the coordinates obtained in 1) may deviate from the real coordinates and the area needs to be enlarged after feathering to achieve the transition effect between the edge and the surrounding pixels, the size of the final matrix should be enlarged 1/5 upward and downward, respectively, by the height of the entire rectangle and 1/10 leftward and rightward, respectively, by the width of the entire rectangle (in most cases, the width of the lip is about 2 times the height).
10) The original formulas of the three image mixing modes are as follows:
stacking the front sheets: c ═ A × B
And (3) superposition: c ═ A × B)/128, A ≤ 128
C＝255–((255–A)*(255-B)/128),A>128 soft light: c ═ A × B/128+ (A/255)2*(255–2*B),B≤128
C ═ a (255-B)/128+ √ (a/255) × (2 × B-255), B >128 since the original matrix has been normalized in step 2), the derivation of the three mixing modes from the normalization equation 10) was performed.
Compared with the method for lip gloss makeup based on different lip morphological characteristics, which is proposed by Chinese patent application No. 201210100239.7, the method is wider in adaptability, and the main upper and lower lip acquisition mode of the method is based on the lip key points returned in the face positioning and recognition method, so that the lip gloss makeup under different light rays is better adapted to be realized. In addition, the method is simpler and faster in flow, does not need complicated classification and evaluation calculation, directly acts on a specific picture position, and achieves good balance in speed and effect.
Compared with the Chinese patent application No. 201410157583.9, the method for enhancing the image of the automatic lip gloss based on the color space has better advantage in the aspect of realizing efficiency. The method does not need to calculate a color space distribution probability chart and calculate and predict the lip pixel probability, can finish making up the lips through an original RGB color channel in the color channel, and has better performance on the calculation efficiency and the effect.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A rapid and real-time lip gloss makeup method is characterized by comprising the following steps:
1) carrying out face recognition on an original image, acquiring key points of facial five sense organs, and selecting feature key points belonging to a lip contour from the key points;
2) loading the original image in an integer RGB color space distribution, and performing normalization processing to ensure that the pixel values of the image are distributed between 0.0 and 1.0;
3) respectively obtaining fitting curves of upper and lower lip contours;
4) acquiring all pixel sets of the curve according to the curve in the step 3), namely the pixel sets of the upper and lower lip outlines;
5) respectively obtaining minimum bounding rectangles of the upper lip and the lower lip according to the characteristic points in the step 1), respectively traversing the minimum bounding rectangles of the upper lip and the lower lip, and judging pixel sets contained in the curves in the rectangles by using the fitted curves in the step 3), namely all pixel sets of the upper lip and the lower lip;
6) constructing an original image 1 according to the upper and lower lip pixel sets obtained in the step 4): a gray Mask image of 1 relationship, in which the pixel values in the upper and lower lips are 1.0 and the remaining pixel values are 0.0;
7) changing the size of the Mask image, and reducing the size of the Mask image in equal proportion;
8) performing Gaussian filtering fuzzy processing on the Mask image to enable the edge of the Mask image to achieve the feathering effect;
9) enlarging the Mask image processed in the step 8) to form 1: 1 in a proportional relationship;
10) performing image mixing processing on the original image subjected to normalization in the step 2), wherein the processing mode is one of a positive film bottom-folding mode, a soft light mode and a superposition mode;
11) step 10), carrying out matrix pixel-by-pixel multiplication on an image RGB three-channel matrix obtained after image mixing processing and a Mask image respectively to obtain a matrix image of upper and lower lips subjected to edge feathering;
12) separating the RGB channel image matrix obtained in the step 11), and multiplying the RGB channel image matrix pixel by pixel with the weight value of R, G, B three channels respectively to achieve the purpose of changing the lip gloss;
13) performing pixel-by-pixel multiplication on the Mask image after the inversion operation and the RGB three-channel matrix of the original image normalized in the step 2) to obtain an image matrix which is the same as the original image but has pixels in upper and lower lips of 0.0;
14) carrying out addition operation on the matrix obtained in the step 11) and the matrix obtained in the step 13), and multiplying the matrix by a transparency coefficient to obtain a result image of synthesis processing;
15) and (5) carrying out reduction processing on the result in the step 14) to obtain a final effect image.
2. The method for making up lip gloss according to claim 1, wherein:
the key points of the characteristics of the lip profile in the step 1) comprise an upper lip and a lower lip.
3. The method for making up lip gloss according to claim 1, wherein:
the step 2) applies linear normalization processing, and the formula is as follows:
C＝(A-MinValue)/(MaxValue-MinValue)
wherein, C is a single pixel value after the original image is converted; a is a single pixel value before the original image is converted; MinValue is the minimum value of the pixels in the original image, and the value is 0.0; MaxValue is the maximum value of the pixels in the original image, and the value is 255.0.
4. The method for making up lip gloss according to claim 1, wherein:
and (3) respectively obtaining fitting curves of the upper lip profile and the lower lip profile by using a Douglas-Peucker algorithm (Douglas-Peucker algorithm).
5. The method for making up lip gloss according to claim 1, wherein:
the gaussian filtering fuzzy processing in the step 8) adopts a transformation formula of each pixel in the normal distribution calculation image as follows:
where u is the mean of a normal distribution; v is the blur radius; σ is the standard deviation of a normal distribution.
6. The method for making up lip gloss according to claim 1, wherein:
the formula corresponding to the processing mode in the step 10) is as follows:
stacking the front sheets: c is A2
And (3) superposition: c is A2*α,A≤1/α
C＝1–(1-A)2*α,A>1/α
Softening the light: c is A2*α+A2*(1-2*A),A≤1/α
C ═ a (1-a) × + √ a (2 × a-1), a >1/α where α is the superposition coefficient, taking a value of 255.0/128.0, and a is the single pixel value in the original image.
7. The method for making up lip gloss according to claim 1, wherein:
the result image of the synthesis processing obtained in the step 14) is as follows:
C＝E*α+B*(1.0-α)，α∈{0,1}
where E is the resulting image matrix in 11), B is the resulting matrix in 13), and α is the transparency coefficient.
8. The method for making up lip gloss according to claim 1, wherein:
the final effect image is obtained in the step 15), and the formula is as follows:
C＝E*(MaxValue-MinValue)+MinValue
wherein E is the resulting image matrix in 11); MinValue is the minimum value of the pixels in the final effect image, and the value is 0.0; MaxValue is the maximum value of the pixels in the final effect image, and the value is 255.0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711494691.5A CN108596992B (en) | 2017-12-31 | 2017-12-31 | Rapid real-time lip gloss makeup method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711494691.5A CN108596992B (en) | 2017-12-31 | 2017-12-31 | Rapid real-time lip gloss makeup method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596992A CN108596992A (en) | 2018-09-28 |
| CN108596992B true CN108596992B (en) | 2021-01-01 |
Family
ID=63633187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711494691.5A Active CN108596992B (en) | 2017-12-31 | 2017-12-31 | Rapid real-time lip gloss makeup method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596992B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584180A (en) * | 2018-11-30 | 2019-04-05 | 深圳市脸萌科技有限公司 | Face image processing process, device, electronic equipment and computer storage medium |
| CN109754375B (en) * | 2018-12-25 | 2021-05-14 | 广州方硅信息技术有限公司 | Image processing method, system, computer device, storage medium and terminal |
| CN111179156B (en) * | 2019-12-23 | 2023-09-19 | 北京中广上洋科技股份有限公司 | Video beautifying method based on face detection |
| CN114339448B (en) * | 2021-12-31 | 2024-02-13 | 深圳万兴软件有限公司 | Method and device for manufacturing special effects of beam video, computer equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668451A (en) * | 2007-03-08 | 2010-03-10 | 惠普开发有限公司 | Method and system for recommending a product based upon skin color estimated from an image |
| CN102013103A (en) * | 2010-12-03 | 2011-04-13 | 上海交通大学 | Method for dynamically tracking lip in real time |
| CN103914699A (en) * | 2014-04-17 | 2014-07-09 | 厦门美图网科技有限公司 | Automatic lip gloss image enhancement method based on color space |
| CN104067311A (en) * | 2011-12-04 | 2014-09-24 | 数码装饰有限公司 | Digital makeup |
| US9058765B1 (en) * | 2008-03-17 | 2015-06-16 | Taaz, Inc. | System and method for creating and sharing personalized virtual makeovers |
| CN105469407A (en) * | 2015-11-30 | 2016-04-06 | 华南理工大学 | Facial image layer decomposition method based on improved guide filter |
| CN105488472A (en) * | 2015-11-30 | 2016-04-13 | 华南理工大学 | Digital make-up method based on sample template |
| CN107123083A (en) * | 2017-05-02 | 2017-09-01 | 中国科学技术大学 | Face edit methods |
| CN107451548A (en) * | 2017-07-19 | 2017-12-08 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5273208B2 (en) * | 2011-06-07 | 2013-08-28 | オムロン株式会社 | Image processing apparatus, image processing method, and control program |
-
2017
- 2017-12-31 CN CN201711494691.5A patent/CN108596992B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668451A (en) * | 2007-03-08 | 2010-03-10 | 惠普开发有限公司 | Method and system for recommending a product based upon skin color estimated from an image |
| US9058765B1 (en) * | 2008-03-17 | 2015-06-16 | Taaz, Inc. | System and method for creating and sharing personalized virtual makeovers |
| CN102013103A (en) * | 2010-12-03 | 2011-04-13 | 上海交通大学 | Method for dynamically tracking lip in real time |
| CN104067311A (en) * | 2011-12-04 | 2014-09-24 | 数码装饰有限公司 | Digital makeup |
| CN103914699A (en) * | 2014-04-17 | 2014-07-09 | 厦门美图网科技有限公司 | Automatic lip gloss image enhancement method based on color space |
| CN105469407A (en) * | 2015-11-30 | 2016-04-06 | 华南理工大学 | Facial image layer decomposition method based on improved guide filter |
| CN105488472A (en) * | 2015-11-30 | 2016-04-13 | 华南理工大学 | Digital make-up method based on sample template |
| CN107123083A (en) * | 2017-05-02 | 2017-09-01 | 中国科学技术大学 | Face edit methods |
| CN107451548A (en) * | 2017-07-19 | 2017-12-08 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
Non-Patent Citations (4)
| Title |
|---|
| A New color transformation for lips segmentation;N. Eveno等;《IEEE Xplore》;20020807;第3-8页 * |
| Lip contour extraction scheme based on K-means clustering in different color planes;F. S. Rahman等;《IEEE Xplore》;20140710;全文 * |
| 人脸虚拟化妆***的研究;祝秀萍等;《计算机与信息技术》;20080831;第38-42页 * |
| 彩色图像人脸检测及人脸特征点定位;刘小林;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120615;第2012年卷(第06期);第I138-2167页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596992A (en) | 2018-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596992B (en) | Rapid real-time lip gloss makeup method | |
| CN109859098B (en) | Face image fusion method and device, computer equipment and readable storage medium | |
| CN103914699B (en) | A kind of method of the image enhaucament of the automatic lip gloss based on color space | |
| Shen et al. | Depth-aware image seam carving | |
| CN108805090B (en) | Virtual makeup trial method based on planar grid model | |
| CN103927727B (en) | Method for converting scalar image into vector image | |
| CN104966285B (en) | A kind of detection method of salient region | |
| CN110853119B (en) | Reference picture-based makeup transfer method with robustness | |
| Kim et al. | Low-light image enhancement based on maximal diffusion values | |
| CN110634147A (en) | Image matting method based on bilateral boot up-sampling | |
| CN116583878A (en) | Method and system for personalizing 3D head model deformation | |
| CN102024156A (en) | Method for positioning lip region in color face image | |
| CN105046278B (en) | The optimization method of Adaboost detection algorithm based on Haar feature | |
| CN105574814A (en) | Portrait paper-cut special effect generation method | |
| CN111489322A (en) | Method and device for adding sky filter to static picture | |
| CN116997933A (en) | Method and system for constructing facial position map | |
| JP2014016688A (en) | Non-realistic conversion program, device and method using saliency map | |
| CN111986212A (en) | Method for realizing flowing special effect of portrait hair | |
| CN114565508B (en) | Virtual reloading method and device | |
| CN113436284A (en) | Image processing method and device, computer equipment and storage medium | |
| CN110111239B (en) | Human image head background blurring method based on tof camera soft segmentation | |
| Lei et al. | Low-light image enhancement using the cell vibration model | |
| WO2022105347A1 (en) | Image processing method and device | |
| CN117157673A (en) | Method and system for forming personalized 3D head and face models | |
| CN111275610B (en) | Face aging image processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |