CN107506559B - Star face shaping makeup recommendation method and device based on face similarity analysis - Google Patents

Star face shaping makeup recommendation method and device based on face similarity analysis Download PDF

Info

Publication number
CN107506559B
CN107506559B CN201710804911.3A CN201710804911A CN107506559B CN 107506559 B CN107506559 B CN 107506559B CN 201710804911 A CN201710804911 A CN 201710804911A CN 107506559 B CN107506559 B CN 107506559B
Authority
CN
China
Prior art keywords
face
local
star
organ
model
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.)
Expired - Fee Related
Application number
CN201710804911.3A
Other languages
Chinese (zh)
Other versions
CN107506559A (en
Inventor
廖海斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201710804911.3A priority Critical patent/CN107506559B/en
Publication of CN107506559A publication Critical patent/CN107506559A/en
Application granted granted Critical
Publication of CN107506559B publication Critical patent/CN107506559B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00Three dimensional [3D] modelling, e.g. data description of 3D objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Processing Or Creating Images (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a star face shaping makeup recommendation method and device based on a star face matching and similarity analysis method. The method comprises the following steps: the method comprises the steps of constructing a 2D/3D face library, preprocessing a face image, reconstructing a three-dimensional face, matching a star face, recommending and visually presenting a star face shaping, and recommending and visually presenting a star face makeup. In order to improve the stability of face matching, the face similarity matching is carried out by adopting 3D shape characteristics; in order to improve the user experience and interest, the shaping and makeup process and effect of the user face are subjected to 3D visual presentation. The invention can be applied to online games and APP development, and can also be applied to the fields of shaping, beautifying and making up.

Description

Star face shaping makeup recommendation method and device based on face similarity analysis
Technical Field
The invention relates to the technical field of image processing, image searching and pattern recognition, in particular to a star face shaping makeup recommendation method and device based on face similarity analysis.
Background
In recent years, people have increasingly raised interest in similar Face search and star Face matching, and some well-known applications such as microsoft twins or not, Face + + similar Face search, hundred-degree star Face, hundred-degree magic map, star Face search, star Face illumination and the like mark that similar Face search is becoming a new round of research hotspot. However, the existing star face matching game is unstable, namely, different stars in matching are caused by the fact that the same person inputs different types of face images frequently. In addition, the current star face game is not very pleasing to the eye. The user does not want to have a context after finding a star like himself or herself, but most users are star-charming, and the user would prefer if further matching interaction with the star face were possible.
Therefore, the invention provides a star face matching method based on a three-dimensional face to improve the stability of human star face matching. In addition, the recommendation of the starred face shaping makeup is provided for the user, and the process and the steps are visually presented. By the method, the stability of star face matching and the user experience are improved, the intervention of shaping and cosmetic advertising is facilitated, and economic benefits are brought to developers.
Disclosure of Invention
In order to solve the problems, the invention provides a star face reshaping makeup recommendation method and device based on face similarity analysis.
The star face shaping makeup recommendation method based on face similarity analysis is characterized by comprising the following steps of:
s1 construction of star 2D/3D face library
Collecting the star face images, carrying out size scale normalization processing to obtain standardized 2D face images, carrying out 3D reconstruction on the standardized 2D star faces by using a 3D reconstruction technology to obtain corresponding 3D face images, and constructing a star 2D/3D face library at least comprising 500 stars in such a way.
The 3D reconstruction technology adopts a 3D deformation model method to carry out 3D reconstruction, and the method comprises the following steps:
suppose a new face image Iinput3D face (S)new,Tnew) Can be represented by a linear combination of the shape vector and the texture vector of the existing 3D face model:
Figure GDA0001441002120000011
wherein S isnIs the shape vector, T, of the 3D face modelnTexture vector as a 3D face model, an,bnRespectively, the combined coefficients of the shape and texture vectors. Then, as long as the combination coefficients (a, b) are present, a 3D reconstruction of the new face image can be performed.
The method for matching the 3D deformation model of the new face image and solving the combination coefficient (a, b) comprises the following steps:
Figure GDA0001441002120000021
wherein, ImodelIs a 2D perspective projection image of the 3D face model, determined by the illumination model and the camera model. The solution of the texture combination coefficient b and so on.
Further, the invention improves the 3D deformation model and provides a face 3D reconstruction method of the local 3D deformation model, which comprises the following steps:
firstly, dividing the face into 5 large organ regions such as forehead, eyebrow, eyes, nose, mouth and the like according to key points of the face, and constructing a 3D face local organ model aiming at each face organ region.
Then, the new face is divided in the same way, and 3D reconstruction is carried out on each 2D face organ region by using the deformation model.
And finally, seamlessly splicing the 3D images of the local organs into a 3D face.
S2 face image preprocessing
And preprocessing the input face image, including face detection, face key point positioning, face normalization and face image quality judgment.
The face detection is characterized in that a traditional Adaboost method or a deep learning face detection method is adopted.
The human face key point positioning method is characterized in that 68 key points of the human face are selected by adopting a traditional SDM (collaborative Description method) or a deep learning method.
The human face normalization is characterized in that human face size scale and illumination normalization are carried out.
The quality judgment of the face image is characterized in that the qualification judgment of the resolution and the posture of the face is carried out.
S3 face image 3D reconstruction
And 3D reconstruction is carried out on the 2D face image subjected to face preprocessing in the step S2 by using the local 3D deformation model, so that a corresponding 3D face image is obtained.
S43D face matching and similarity analysis
And performing similar face search by using the 3D face shape information, matching a star face most similar to the input face, and analyzing the similarity of the similar star face.
The similar face search is characterized in that the similarity matching is carried out by utilizing the shape combination coefficient in the 3D reconstruction process:
firstly, inputting 3D reconstruction shape coefficient a of each local organ of human facenLocal organ matching is performed as a feature vector, and the cosine between two vector angles is used as a similarity measure between two local organs:
Figure GDA0001441002120000031
wherein, an,anThe feature vectors for two matching local organs (the linear combination of local organs represents the weight).
Then, the similarity of each local organ is weighted and summed to obtain the final face similarity.
The star face similarity analysis is characterized in that overall similarity, local organ similarity, most similar local organs and least similar local organs are given.
S5 face shaping recommendation and visual presentation
And recommending a user shaping scheme according to the star face similarity analysis condition. For example, the least similar organs are recommended to be shaped, and the shaping process and the effect graph are shown to the user in a 3D form.
Furthermore, the user can select the shaping scheme according to the requirement and preference of the user. Such as enlarging forehead, eyebrow, double-edged eyelid, removing eye bags, enlarging nose, enlarging Yintang, opening inner canthus, lying silkworm, filling temple, enlarging apple muscle, enlarging cheek fovea, dissolving chin line, dissolving masseter, enlarging lip, filling chin, removing wrinkle, and improving line carving.
Further, the face shaping process and the effect graph of the user are subjected to 3D visual presentation.
S6 face makeup recommendation and visual presentation
And recommending a star face makeup scheme to the user, and visually presenting the effect of each step in the makeup process.
The cosmetic process comprises the following steps: make-up, eyebrow, eye shadow, eyeliner, mascara, blush, and lipstick.
A star face shaping makeup recommendation device based on face similarity analysis is characterized by comprising:
and the storage unit is used for storing the 2D/3D star face images and the star face characteristic vectors. Wherein the feature vector is a 3D reconstructed shape combination coefficient for each local organ.
And the image processing unit is used for face detection, key point positioning, normalization and image quality judgment.
And the three-dimensional reconstruction unit is used for performing 3D reconstruction on the input 2D face.
And the face matching unit is used for carrying out star face similarity matching and finding out the star face most similar to the user.
And the shaping visual presentation unit is used for 3D visual display of the shaping process and effect of the user. The shaping effect display comprises the following steps: the method comprises the steps of enlarging forehead, eyebrow, double eyelids, removing eye bags, enlarging nose, enlarging Yintang, opening inner canthus, laying silkworms, filling temples, enlarging apple muscles, enlarging cheek pits, dissolving chin line, dissolving masseter, enlarging lips, filling chin, removing crinkles, and improving line carving.
And the makeup visual presentation unit is used for displaying the makeup process and effect of the user. The makeup process and effect display comprises the following steps: make-up foundation, eyebrow, eye shadow, eyeliner, eyelash, blush, and lipstick.
Drawings
Fig. 1 is a flowchart of a star face shaping makeup recommendation method based on face similarity analysis.
Fig. 2 is a configuration diagram of a star face shaping makeup recommendation apparatus based on face similarity analysis.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. In an exemplary embodiment, a mobile phone-based game matching with a celebrity is taken as an example for explanation. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1:
fig. 1 shows a flow of implementation of a star shaping makeup recommendation method based on face similarity analysis, which is detailed as follows:
s101, construction of star 2D/3D face library
And collecting the star face images, and carrying out size scale normalization processing to obtain standardized 2D face images. And 3D reconstruction is carried out on the standardized 2D star face by utilizing a 3D reconstruction technology to obtain a corresponding 3D face image.
The collected star 2D face images have the following standards: the front and five sense organs are clear.
The 3D face image is obtained by 3D reconstruction through a 3D deformation model method, and the method comprises the following steps:
suppose a new face image Iinput3D face (S)new,Tnew) Can be represented by a linear combination of the shape vector and the texture vector of the existing 3D face model:
Figure GDA0001441002120000041
wherein S isnIs the shape vector of the 3D face, TnTexture vector of 3D face, an,bnRespectively, the combined coefficients of the shape and texture vectors. Then, as long as the combination coefficients (a, b) are present, a 3D reconstruction of the new face image can be performed.
The method for matching the 3D deformation model of the new face image and solving the combination coefficient (a, b) comprises the following steps:
Figure GDA0001441002120000042
wherein, ImodelIs a 2D perspective projection image of the 3D face model, determined by the illumination model and the camera model. The solution of the texture combination coefficient b and so on.
The existing 3D face model is characterized in that the 3D face model of 500 objects is acquired by a 3D scanner.
Further, the invention improves the 3D deformation model and provides a face 3D reconstruction method of the local 3D deformation model, which comprises the following steps:
firstly, dividing the face into 5 large organ regions such as forehead, eyebrow, eyes, nose, mouth and the like according to key points of the face, and constructing a 3D face local organ dictionary aiming at each face organ region.
Then, the new face is divided in the same way, and 3D reconstruction is carried out on each 2D face organ region by using the deformation model.
And finally, seamlessly splicing the 3D images of the local organs into a 3D face.
Further, this step stores the combination coefficients of the 3D reconstruction of each local organ as the shape feature vector of the local organ.
S102 human face image preprocessing
And preprocessing the input face image, such as face detection, key point positioning, normalization, image quality judgment and the like. And if the quality judgment of the face image is unqualified, prompting the user to resubmit the image only until the image is qualified.
The face detection is characterized in that the face detection is carried out by adopting a traditional Adaboost method or a deep learning method.
The human face key point positioning method is characterized in that 68 key points of the human face are selected by adopting a traditional SDM (collaborative Description method) or a deep learning method.
The human face normalization is characterized in that the human face is cut according to human face key points (eyebrow dust points, chin points and ear key points) and then size scale and illumination normalization are carried out.
The quality judgment of the face image is characterized in that the qualification judgment of the resolution and the posture of the face is carried out. And if the proportion of the face image to the whole image is less than 1/3 and the interpupillary distance is less than 40, the resolution of the face image is not qualified. And if any one of the left, right, upper and lower deflection of the human face is more than 30 degrees, determining that the posture of the human face image is unqualified.
S103 human face image 3D reconstruction
And 3D reconstruction is carried out on the 2D face image subjected to the face preprocessing in the step S102 by using the local 3D deformation model, so that the corresponding 3D face image and the shape combination coefficient of each local organ are obtained.
The 3D reconstruction method is the same as the 3D reconstruction method in the step S101.
S1043D face matching and similarity analysis
And performing similar face search by using the 3D face shape information, matching a star face most similar to the input face, and analyzing the similarity of the similar star face.
The similar face search is characterized in that the similarity matching is carried out by utilizing the shape combination coefficient in the 3D reconstruction process:
firstly, inputting 3D reconstruction shape coefficient a of each local organ of human facenLocal organ matching is performed as a feature vector, and the cosine between two vector angles is used as a similarity measure between two local organs:
Figure GDA0001441002120000061
wherein, an,anThe feature vectors for two matching local organs (the linear combination of local organs represents the weight).
Then, weighting and summing the similarity of each local organ to obtain the final face similarity, wherein the weighting and summing rule is as follows:
θ=wfθf+wbθb+weθe+wnθn+wmθm
where θ is the final similarity, θfbenmSimilarity of forehead, eyebrow, eye, nose and mouth, ws=0.2,wb=0.3,we=0.1,wn=0.2,wmThe weights of forehead, eyebrow, eyes, nose and mouth are 0.2.
The star face similarity analysis is characterized in that overall similarity, local organ similarity, most similar local organs and least similar local organs are given.
S105 face shaping recommendation and visual presentation
And recommending a user shaping scheme according to the star face similarity analysis condition. For example, the least similar organ (nose) is recommended for plastic-hump nose plastic recommendation. And the shaping process and the effect graph are shown to the user in a 3D form.
Furthermore, the user can select a shaping scheme according to own preference, such as enlarging forehead, eyebrow, double-edged eyelid, removing eye bags, enlarging nose, enlarging Yintang, opening inner canthus, laying silkworms, filling temple, enlarging apple muscle, enlarging cheek fovea, dissolving chin line, dissolving masseter muscle, enlarging lip, filling chin, removing stature line and improving line carving.
S106 face makeup recommendation and visual presentation
And recommending a star face makeup scheme to the user, and visually presenting the effect of each step in the makeup process.
The cosmetic process and visual effect presentation steps include: make-up foundation, eyebrow, eye shadow, eyeliner, eyelash, blush, and lipstick.
Example 2:
fig. 2 is a block diagram of a star face shaping makeup recommendation device based on face similarity analysis, which is detailed as follows:
and the storage unit is used for storing the 2D/3D star face images and the star face characteristic vectors. Wherein the feature vector is a 3D reconstructed shape combination coefficient for each local organ.
And the image processing unit is used for face detection, key point positioning, normalization and image quality judgment.
And the three-dimensional reconstruction unit is used for performing 3D reconstruction on the input 2D face. Wherein, the 3D reconstruction adopts a 3D local deformation model method.
And the face matching unit is used for carrying out star face similarity matching, finding out a star face most similar to the user and carrying out similarity analysis.
And the shaping visual presentation unit is used for 3D displaying the micro-shaping process and effect of the user. The micro-plastic effect display comprises the following steps: the method comprises the steps of enlarging forehead, eyebrow, double eyelids, removing eye bags, enlarging nose, enlarging Yintang, opening inner canthus, laying silkworms, filling temples, enlarging apple muscles, enlarging cheek pits, dissolving chin line, dissolving masseter, enlarging lips, filling chin, removing crinkles, and improving line carving.
And the makeup visual presentation unit is used for displaying the makeup process and effect of the user. The makeup process and effect display comprises the following steps: make-up foundation, eyebrow, eye shadow, eyeliner, eyelash, blush, and lipstick.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (5)

1. A star face shaping makeup recommendation method based on face similarity analysis is characterized by comprising the following steps:
constructing a star 2D/3D face library: collecting star face images, carrying out size scale normalization processing on the star face images to obtain standardized 2D face images, carrying out 3D reconstruction on the standardized 2D star faces by using a 3D reconstruction technology to obtain corresponding 3D face images, and constructing a star 2D/3D face library at least comprising 500 stars in the mode;
preprocessing a face image: preprocessing a face image input by a user, including face detection, face key point positioning, face normalization and face image quality judgment;
3D reconstruction of a face image: 3D reconstruction is carried out on the preprocessed user face image by using a local 3D deformation model method to obtain a corresponding 3D face image; the method of the local 3D deformation model comprises the following steps: firstly, dividing a human face into 5 large facial organ regions of the forehead, eyebrows, eyes, a nose and a mouth according to key points of the human face, and constructing a 3D human face local organ model aiming at each human face organ region at the background to complete the construction of a human face local organ 3D model dictionary;
then, the new face is divided in the same way, and 3D reconstruction is carried out on each 2D face organ region by using a 3D deformation model:
suppose a new face local organ image IinputIs represented as (S)new,Tnew) Then, it can be represented by the linear combination of the shape vector and the texture vector of the existing 3D face local organ model:
Figure FDA0002907187660000011
wherein S isnAs a shape vector, T, of a 3D face local organ modelnTexture vector of local organ model of 3D human face, an,bnThe combined coefficients are respectively the shape vector and the texture vector, so that the new face local organ image can be subjected to 3D reconstruction as long as the combined coefficients (a, b) exist;
assuming that 3D deformation model matching is performed on the new face local organ image, the problem of solving the combination coefficients (a, b) turns into:
Figure FDA0002907187660000012
wherein, ImodelThe method is characterized in that 2D perspective projection images of a 3D face local organ model are determined by an illumination model and a camera model, and the solution of a texture combination coefficient b is analogized; finally, seamlessly splicing the 3D images of the local organs into a 3D face image;
3D face matching and similarity analysis: carrying out similar face search by using the 3D face shape information, matching a star face most similar to the input face, and giving a similarity analysis result of the similar star face; the similar face searching method is to use the shape combination coefficient in the 3D reconstruction process to carry out similarity matching: firstly, inputting 3D reconstruction shape coefficient a of each local organ of human facenLocal organ matching is performed as a feature vector, and the cosine between two vector angles is used as a similarity measure between two local organs:
Figure FDA0002907187660000021
wherein (a)n,a′n) A pair of local organ combination coefficient feature vectors; then, weighting and summing the similarity of each local organ to obtain the final face similarity;
face shaping recommendation and visual presentation: recommending a user shaping scheme according to the star face similarity analysis condition, and displaying a shaping process and an effect diagram to a user in a 3D form; or selecting a corresponding shaping scheme according to personal shaping requirements and preferences of a user, and performing 3D visual display of the shaping process and the shaping effect;
face makeup recommendation and visual presentation: and recommending a star face makeup scheme to the user, and visually presenting the effect of each step in the makeup process.
2. A star face shaping makeup recommendation method based on face similarity analysis according to claim 1, characterized in that said star face similarity analysis comprises: global similarity, local organ similarity, most similar local organs, and least similar local organs.
3. A star face shaping cosmetic recommendation method based on face similarity analysis according to claim 1, wherein the shaping recommendation scheme comprises: enlarging forehead, eyebrow, double-edged eyelid, removing eye bag, enlarging nose, enlarging Yintang, opening inner canthus, lying silkworm, filling temple, enlarging apple muscle, enlarging concave cheek, dissolving chin line, dissolving masseter muscle, enlarging lip, filling chin, and improving wrinkle and line carving.
4. The method for recommending a star face shaping makeup based on a face similarity analysis according to claim 1, wherein said makeup procedure effect presentation comprises: make-up, eyebrow, eye shadow, eyeliner, mascara, blush, and lipstick.
5. A star face shaping makeup recommendation device based on face similarity analysis is characterized by comprising: the storage unit is used for storing a star 2D/3D face image and a star face feature vector, wherein the feature vector is a 3D reconstruction shape combination coefficient of each local organ;
the image processing unit is used for face detection, key point positioning, normalization and image quality judgment;
the three-dimensional reconstruction unit is used for performing 3D reconstruction on the input 2D face, and the 3D reconstruction adopts a local 3D deformation model method: firstly, dividing a human face into 5 large facial organ regions of the forehead, eyebrows, eyes, a nose and a mouth according to key points of the human face, and constructing a 3D human face local organ model aiming at each human face organ region at the background to complete the construction of a human face local organ 3D model dictionary;
then, the new face is divided in the same way, and 3D reconstruction is carried out on each 2D face organ region by using a 3D deformation model:
suppose a new face local organ image IinputIs represented as (S)new,Tnew) Then, it can be represented by the linear combination of the shape vector and the texture vector of the existing 3D face local organ model:
Figure FDA0002907187660000022
wherein S isnAs a shape vector, T, of a 3D face local organ modelnTexture vector of local organ model of 3D human face, an,bnThe combined coefficients are respectively the shape vector and the texture vector, so that the new face local organ image can be subjected to 3D reconstruction as long as the combined coefficients (a, b) exist;
assuming that 3D deformation model matching is performed on the new face local organ image, the problem of solving the combination coefficients (a, b) turns into:
Figure FDA0002907187660000031
wherein, ImodelThe method is characterized in that 2D perspective projection images of a 3D face local organ model are determined by an illumination model and a camera model, and the solution of a texture combination coefficient b is analogized; finally, seamlessly splicing the 3D images of the local organs into a 3D face image;
a face matching unit for performing star face similarity matching to find the best match with the userA similar starry face; the face matching method is to use the shape combination coefficient in the 3D reconstruction process to carry out similarity matching: firstly, inputting 3D reconstruction shape coefficient a of each local organ of human facenLocal organ matching is performed as a feature vector, and the cosine between two vector angles is used as a similarity measure between two local organs:
Figure FDA0002907187660000032
wherein (a)n,a′n) A pair of local organ combination coefficient feature vectors; then, weighting and summing the similarity of each local organ to obtain the final face similarity;
the plastic vision presents the unit for 3D vision shows the process and the effect of user's plastic, and plastic effect show includes: enlarging forehead, eyebrow, double eyelids, removing eye bags, enlarging nose, enlarging Yintang, opening inner canthus, laying silkworm, filling temple, enlarging apple muscle, enlarging concave cheek, dissolving chin line, dissolving masseter, enlarging lip, filling chin, removing wrinkle, and improving line carving;
the makeup visual presentation unit is used for displaying the makeup process and effect of a user, and the makeup process and effect display comprises the following steps: make-up foundation, eyebrow, eye shadow, eyeliner, eyelash, blush, and lipstick.
CN201710804911.3A 2017-09-08 2017-09-08 Star face shaping makeup recommendation method and device based on face similarity analysis Expired - Fee Related CN107506559B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710804911.3A CN107506559B (en) 2017-09-08 2017-09-08 Star face shaping makeup recommendation method and device based on face similarity analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710804911.3A CN107506559B (en) 2017-09-08 2017-09-08 Star face shaping makeup recommendation method and device based on face similarity analysis

Publications (2)

Publication Number Publication Date
CN107506559A CN107506559A (en) 2017-12-22
CN107506559B true CN107506559B (en) 2021-03-23

Family

ID=60695268

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710804911.3A Expired - Fee Related CN107506559B (en) 2017-09-08 2017-09-08 Star face shaping makeup recommendation method and device based on face similarity analysis

Country Status (1)

Country Link
CN (1) CN107506559B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110110118B (en) * 2017-12-27 2021-11-16 Oppo广东移动通信有限公司 Dressing recommendation method and device, storage medium and mobile terminal
CN108053365B (en) * 2017-12-29 2019-11-05 百度在线网络技术(北京)有限公司 Method and apparatus for generating information
CN108229415B (en) * 2018-01-17 2020-12-22 Oppo广东移动通信有限公司 Information recommendation method and device, electronic equipment and computer-readable storage medium
CN110136270A (en) * 2018-02-02 2019-08-16 北京京东尚科信息技术有限公司 The method and apparatus of adornment data are held in production
CN108898546B (en) * 2018-06-15 2022-08-16 北京小米移动软件有限公司 Face image processing method, device and equipment and readable storage medium
CN109189967A (en) * 2018-08-24 2019-01-11 微云(武汉)科技有限公司 A kind of lift face proposal recommending method, device and storage medium based on recognition of face
CN109061892A (en) * 2018-09-27 2018-12-21 广州狄卡视觉科技有限公司 Plastic surgery medical image Model Reconstruction interacts naked-eye stereoscopic display system and method
CN109598203A (en) * 2018-11-06 2019-04-09 平安科技(深圳)有限公司 Photo adding method, device, terminal and storage medium based on recognition of face
CN110473608B (en) * 2019-06-27 2022-04-19 上海合智医疗科技有限公司 Method, system, device and storage medium for simulating postoperative effect of double-eyelid surgery
CN111062260B (en) * 2019-11-25 2024-03-05 杭州绿度信息技术有限公司 Automatic generation method of face-beautifying recommendation scheme
CN111966852B (en) * 2020-06-28 2024-04-09 北京百度网讯科技有限公司 Face-based virtual face-lifting method and device
CN114333018A (en) * 2021-12-29 2022-04-12 北京百度网讯科技有限公司 Shaping information recommendation method and device and electronic equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968802A (en) * 2010-09-30 2011-02-09 百度在线网络技术(北京)有限公司 Method and equipment for recommending content of Internet based on user browse behavior
CN102708575A (en) * 2012-05-17 2012-10-03 彭强 Daily makeup design method and system based on face feature region recognition
CN102982165A (en) * 2012-12-10 2013-03-20 南京大学 Large-scale human face image searching method
CN104851123A (en) * 2014-02-13 2015-08-19 北京师范大学 Three-dimensional human face change simulation method
CN106033621A (en) * 2015-03-17 2016-10-19 阿里巴巴集团控股有限公司 Three-dimensional modeling method and device
CN106778468A (en) * 2016-11-14 2017-05-31 深圳奥比中光科技有限公司 3D face identification methods and equipment

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9907473B2 (en) * 2015-04-03 2018-03-06 Koninklijke Philips N.V. Personal monitoring system
US20130287294A1 (en) * 2012-04-30 2013-10-31 Cywee Group Limited Methods for Generating Personalized 3D Models Using 2D Images and Generic 3D Models, and Related Personalized 3D Model Generating System

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968802A (en) * 2010-09-30 2011-02-09 百度在线网络技术(北京)有限公司 Method and equipment for recommending content of Internet based on user browse behavior
CN102708575A (en) * 2012-05-17 2012-10-03 彭强 Daily makeup design method and system based on face feature region recognition
CN102982165A (en) * 2012-12-10 2013-03-20 南京大学 Large-scale human face image searching method
CN104851123A (en) * 2014-02-13 2015-08-19 北京师范大学 Three-dimensional human face change simulation method
CN106033621A (en) * 2015-03-17 2016-10-19 阿里巴巴集团控股有限公司 Three-dimensional modeling method and device
CN106778468A (en) * 2016-11-14 2017-05-31 深圳奥比中光科技有限公司 3D face identification methods and equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
《基于局部形变模型三维人脸快速建模》;郝宁波 等;《视频应用与工程》;20111231;89-92、105 *
《基于特征点的三维人脸形变模型》;龚勋 等;《计算机图形学与计算机辅助设计》;20091231;724-733 *

Also Published As

Publication number Publication date
CN107506559A (en) 2017-12-22

Similar Documents

Publication Publication Date Title
CN107506559B (en) Star face shaping makeup recommendation method and device based on face similarity analysis
US20230351663A1 (en) System and method for generating an avatar that expresses a state of a user
CN114663199B (en) Dynamic display real-time three-dimensional virtual fitting system and method
US10799010B2 (en) Makeup application assist device and makeup application assist method
Bruce et al. Sex discrimination: how do we tell the difference between male and female faces?
CN101055647B (en) Method and device for processing image
CN108701216A (en) A kind of face shape of face recognition methods, device and intelligent terminal
US20220148333A1 (en) Method and system for estimating eye-related geometric parameters of a user
CN107563336A (en) Human face similarity degree analysis method, the device and system of game are matched for famous person
CN107025678A (en) A kind of driving method and device of 3D dummy models
CN111414839A (en) Emotion recognition method and device based on gestures
CN110796593A (en) Image processing method, device, medium and electronic equipment based on artificial intelligence
CN105118023A (en) Real-time video human face cartoonlization generating method based on human facial feature points
US20220044311A1 (en) Method for enhancing a user's image while e-commerce shopping for the purpose of enhancing the item that is for sale
Davis et al. An expressive three-mode principal components model for gender recognition
CN108932654A (en) A kind of virtually examination adornment guidance method and device
KR101913811B1 (en) A method for analysing face information, and an appratus for analysing face information to present faces, identify mental status or compensate it
CN106446207B (en) Makeups library banking process, personalized makeups householder method and its device
Xia et al. Semantic translation of face image with limited pixels for simulated prosthetic vision
KR20180110842A (en) Customized semi-permanent make-up recommendation system based on virtual experience and its service method
CN113947520A (en) Method for realizing face makeup conversion based on generation of confrontation network
JP4893968B2 (en) How to compose face images
CN113628739B (en) Human body data processing method and device
Kumar et al. Multi modal adaptive normalization for audio to video generation
CN110069716A (en) A kind of makeups recommended method, system and computer readable storage medium

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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210323

CF01 Termination of patent right due to non-payment of annual fee