CN113592591B - Face recognition-based dressing recommendation system - Google Patents
Face recognition-based dressing recommendation system Download PDFInfo
- Publication number
- CN113592591B CN113592591B CN202110858375.1A CN202110858375A CN113592591B CN 113592591 B CN113592591 B CN 113592591B CN 202110858375 A CN202110858375 A CN 202110858375A CN 113592591 B CN113592591 B CN 113592591B
- Authority
- CN
- China
- Prior art keywords
- dressing
- score
- face
- matching
- forehead
- 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
- 230000001815 facial effect Effects 0.000 claims abstract description 78
- 239000003086 colorant Substances 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 10
- 210000001061 forehead Anatomy 0.000 claims description 149
- 210000001508 eye Anatomy 0.000 claims description 148
- 238000000605 extraction Methods 0.000 claims description 26
- 239000002537 cosmetic Substances 0.000 claims description 4
- 210000001331 nose Anatomy 0.000 description 95
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a face recognition-based makeup recommendation system, which comprises: the system comprises a storage module, a recording module and a processing module, wherein the storage module stores a plurality of facial features and a plurality of makeup types, the recording module is used for recording facial image data of a user, and the processing module is used for processing according to the acquired facial image data and matching a set of makeup for the user; the several facial features include: several hairstyles, several facial forms, and several skin colors; the several kinds of makeup looks include: several facial forms match the makeup; the memory module further includes: the invention can rapidly and effectively recommend a set of makeup matching with the facial features of the user to solve the problems that the existing makeup recommendation method is too general and experience feeling is poor when the user uses the method.
Description
Technical Field
The invention relates to the technical field of makeup identification, in particular to a face identification-based makeup recommendation system.
Background
The makeup uses cosmetics and tools, adopts the steps and skills in order to render, draw and arrange the face, the five sense organs and other parts of the human body, enhances the stereoscopic impression, adjusts the shape and color, masks the defects and shows the look, thereby achieving the purpose of beautifying the visual feeling. Make-up, can show the unique natural beauty of the personage; the original shape, color and quality of the character can be improved, and the aesthetic feeling and the charm are increased; can be used as an artistic form to present a visual feast and express a feeling. It is emphasized that makeup is not female-specific, and not sex-limiting, and that the frequency of male makeup is increasing in reality, and in real life, proper makeup is also a behavior that respects others.
In the prior art, most people make up according to preference, and make up is self-learned according to the network for some trend makeup, but the best of the makeup is not clear, and in the existing art for recommending the makeup, the function for recommending the makeup is single, a set of reasonable makeup can not be carefully recommended for the user, and the recommendation method is too general and not specific, so that the use experience of the user is poor.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a makeup recommendation system based on facial recognition, which can rapidly and effectively recommend a set of makeup matched with facial features for users so as to solve the problems that the existing makeup recommendation method is too general and experience feeling is poor when in use.
In order to achieve the above object, the present invention is realized by the following technical scheme: a face recognition based cosmetic recommendation system comprising: the system comprises a storage module, a recording module and a processing module, wherein the storage module stores a plurality of facial features and a plurality of makeup types, the recording module is used for recording facial image data of a user, and the processing module is used for processing according to the acquired facial image data and matching a set of makeup for the user;
the several facial features include: several hairstyles, several facial forms, and several skin colors;
the several kinds of makeup looks include: several facial forms match the makeup;
the memory module further includes: the first score corresponding unit is configured with a first score corresponding strategy, and the first score corresponding strategy comprises the following steps: scoring a plurality of facial form matching makeup corresponding to each facial form, hairstyle and skin color, and setting the facial form matching makeup score, the hairstyle corresponding to the facial form matching makeup score and the skin color corresponding to the facial form matching makeup score respectively;
the admission module comprises: the first recording unit is used for recording the whole picture of the user;
the processing module comprises: the device comprises a feature extraction unit and a matching unit, wherein the feature extraction unit is used for extracting features in a picture of a user as a whole, and the matching unit is used for matching makeup according to the combination of the extracted features;
the feature extraction unit is configured with a first extraction policy comprising: extracting a hairstyle, a facial form and skin colors in the whole picture of the user, and comparing the hairstyles, the facial forms and the skin colors with a plurality of hairstyles, a plurality of facial forms and a plurality of skin colors in a storage module to obtain corresponding matched hairstyles, matched facial forms and matched skin colors;
the matching unit is configured with a first matching policy comprising: the face type matching method comprises the steps of obtaining face type matching dressing scores, hair style matching facial types and facial type matching dressing scores corresponding to a plurality of face type matching dressing styles, hair style matching facial type matching dressing scores and facial type matching dressing scores corresponding to skin colors, adding the face type dressing scores, the hair style matching dressing scores and the facial type matching dressing scores corresponding to skin colors of each group to obtain a face type dressing total score, and selecting a group of corresponding face type matching dressing scores with the highest face type dressing total score as a final face type recommended dressing.
Further, the plurality of face shapes further includes: several forehead contours, several face contours, several nose contours, several mouth contours, and several eye contours;
the several kinds of makeup looks still include: several facial matching make-up, several nose matching make-up, several mouth matching make-up and several eyes matching make-up.
Further, the storage module further includes: a second score correspondence unit configured with a second score correspondence policy including: performing forehead matching dressing scores on each forehead contour, face contour, nose contour, mouth contour and eye contour respectively, and setting the forehead dressing scores, face corresponding forehead dressing scores, nose corresponding forehead dressing scores, mouth corresponding forehead dressing scores and eye corresponding forehead dressing scores respectively;
respectively carrying out face matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the face makeup score, the nose corresponding face makeup score, the mouth corresponding face makeup score and the eye corresponding face makeup score;
nose matching makeup scores are respectively carried out on each forehead outline, face outline, nose outline, mouth outline and eye outline, and the nose matching makeup scores are respectively set as a forehead corresponding nose makeup score, a face corresponding nose makeup score, a mouth corresponding nose makeup score and an eye corresponding nose makeup score;
performing mouth matching dressing scores on each forehead outline, face outline, nose outline, mouth outline and eye outline respectively, and setting the mouth matching dressing scores, face matching mouth dressing scores, nose matching mouth dressing scores, mouth dressing scores and eye matching mouth dressing scores as corresponding forehead dressing scores;
and respectively carrying out eye matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the eye matching makeup scoring, the face corresponding eye makeup scoring, the nose corresponding eye makeup scoring, the mouth corresponding eye makeup scoring and the eye makeup scoring.
Further, the recording module further includes: and the second recording unit is used for recording pictures of the face of the user.
Further, the feature extraction unit is further configured to extract features in a picture of a face of the user, and the feature extraction unit is further configured with a second extraction policy, where the second extraction policy includes: and extracting the forehead outline, the face outline, the nose outline, the mouth outline and the eye outline in the face picture of the user, and respectively comparing the forehead outline, the face outline, the mouth outline and the eye outline with a plurality of forehead outlines, a plurality of face outlines, a plurality of nose outlines, a plurality of mouth outlines and a plurality of eye outlines in the storage module to obtain corresponding matched forehead, matched face, matched nose, matched mouth and matched eyes.
Further, the matching unit is further configured with a second matching policy, the second matching policy comprising: obtaining a forehead dressing score, a face corresponding forehead dressing score, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score of a plurality of forehead matching dressing scores corresponding to a matching face, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score, adding the forehead dressing score, the face corresponding forehead dressing score, the nose corresponding forehead dressing score, the mouth corresponding forehead dressing score and the eye corresponding forehead dressing score of each group of forehead dressing scores to obtain a forehead dressing total score, and selecting a group of corresponding forehead matching dressing scores with the highest forehead dressing total score as a final forehead recommended dressing score;
obtaining a forehead corresponding face dressing score, a nose corresponding face dressing score, a mouth corresponding face dressing score and an eye corresponding face dressing score of a plurality of face matching dressing scores corresponding to a matched forehead, adding the face dressing score, the nose corresponding face dressing score, the mouth corresponding face dressing score and the eye corresponding face dressing score of each group of forehead corresponding face dressing score, mouth corresponding face dressing score and eye corresponding face dressing score to obtain a face dressing total score, and selecting a group of corresponding face matching dressing scores with the highest face dressing total score as a final face recommendation dressing score;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding nose dressing score, a face corresponding nose dressing score, a mouth corresponding nose dressing score and an eye corresponding nose dressing score of a matched eye corresponding to a plurality of nose matching dressing, adding the nose dressing score, the face corresponding nose dressing score, the mouth corresponding nose dressing score and the eye corresponding nose dressing score of each group of forehead corresponding nose dressing score to obtain a nose dressing total score, and selecting a group of corresponding nose matching dressing with the highest nose dressing total score as a final nose recommendation dressing;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding mouth dressing score, a face corresponding mouth dressing score, a nose corresponding mouth dressing score, a mouth dressing score and an eye corresponding mouth dressing score of a plurality of mouth matching dressing, adding the forehead corresponding mouth dressing score, the face corresponding mouth dressing score, the nose corresponding mouth dressing score, the mouth dressing score and the eye corresponding mouth dressing score of each group to obtain a mouth dressing total score, and selecting a group of corresponding mouth matching dressing with the highest mouth dressing total score as a final mouth recommendation dressing;
the method comprises the steps of obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding eye dressing score, a face corresponding eye dressing score, a nose corresponding eye dressing score, a mouth corresponding eye dressing score and an eye dressing score of a matched eye corresponding to a plurality of eye matching dressing, adding the forehead corresponding eye dressing score, the face corresponding eye dressing score, the nose corresponding eye dressing score, the mouth corresponding eye dressing score and the eye dressing score to obtain an eye dressing total score, and selecting a group of corresponding eye matching dressing with the highest eye dressing total score as a final eye recommendation dressing.
The invention has the beneficial effects that: the invention obtains the corresponding matching hairstyle, matching facial form and matching skin color by scoring a plurality of facial form matching makeup corresponding to each facial form, hairstyle and skin color and respectively setting the facial form matching makeup score, the hairstyle corresponding to the facial form matching makeup score and the skin color corresponding to the facial form matching makeup score, extracting the hairstyle, the facial form and the skin color in the whole picture of the user through the feature extraction unit and comparing the hairstyle, the facial form and the skin color with a plurality of hairstyles, a plurality of facial forms and a plurality of skin colors in the storage module, and finally, obtaining face type dressing scores of the matching face types, the matching hairstyles and the matching complexion corresponding to a plurality of face type matching dressing styles, the matching dressing scores of the hairstyles and the matching dressing scores of the complexion corresponding to the face types, adding the face type matching dressing scores of each group of face type dressing scores, the hairstyles corresponding to the face type matching dressing scores and the matching dressing scores of the complexion corresponding to the face types to obtain a face type dressing total score, and selecting a group of corresponding face type matching dressing with the highest face type dressing total score as a final face type recommended dressing.
According to the invention, the face shapes are subdivided into the forehead contours, the face contours, the nose contours, the mouth contours and the eye contours, and the subdivided features are respectively matched with the makeup, so that the meticulous nature of the makeup recommendation can be improved, and the rationality and the practicality of the makeup recommendation are further improved.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a schematic block diagram of a first embodiment of the present invention;
fig. 2 is a schematic block diagram of a second embodiment of the present invention.
In the figure: 1. a recommendation system; 11. a storage module; 111. a first score correspondence unit; 112. a second score correspondence unit; 12. a processing module; 121. a feature extraction unit; 122. a matching unit; 13. a recording module; 131. a first recording unit; 132. and a second recording unit.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Referring to fig. 1, in the first embodiment, a complete set of makeup system is recommended based on the hairstyle, face shape and skin color of the user; a face recognition based cosmetic recommendation system comprising: the face pack comprises a storage module 11, a recording module 13 and a processing module 12, wherein the storage module 11 stores a plurality of facial features and a plurality of makeup types, the recording module 13 is used for recording facial image data of a user, and the processing module 12 is used for processing according to the acquired facial image data and matching a set of makeup for the user; the recommendation system 1 is respectively connected with a user side and a maintenance side, the user side obtains a set of makeup recommendation through identification processing of the recommendation system 1 after logging in, and the maintenance side can update a database to continuously provide new makeup.
The several facial features include: several hairstyles, several facial forms, and several skin colors; the several kinds of makeup looks include: several facial forms match the makeup.
The memory module 11 further includes: a first score corresponding unit 111, the first score corresponding unit 111 being configured with a first score corresponding policy, the first score corresponding policy comprising: scoring a plurality of facial form matching makeup corresponding to each facial form, hairstyle and skin color, and setting the facial form matching makeup score, the hairstyle corresponding to the facial form matching makeup score and the skin color corresponding to the facial form matching makeup score respectively; the dressing can be continuously updated and increased in the storage module 11, and the corresponding scores are respectively set, so that the dressing recommendation types of users are continuously increased, meanwhile, the storage module 11 is provided with a self-defined functional unit, and staff at a processing end can adjust the dressing scores according to weather, seasons, working environments and the like, so that the rationality of dressing recommendation can be further improved.
The recording module 13 includes: the first recording unit 131 is used for recording the whole picture of the user; the processing module 12 includes: the device comprises a feature extraction unit 121 and a matching unit 122, wherein the feature extraction unit 121 is used for extracting features in a picture of the whole user, and the matching unit 122 is used for matching the makeup according to the combination of the extracted features.
The feature extraction unit 121 is configured with a first extraction policy including: and extracting the hairstyles, the facial forms and the skin colors in the whole picture of the user, and comparing the hairstyles, the facial forms and the skin colors with a plurality of hairstyles, a plurality of facial forms and a plurality of skin colors in the storage module 11 to obtain corresponding matched hairstyles, matched facial forms and matched skin colors.
The matching unit 122 is configured with a first matching policy, which includes: the face type matching method comprises the steps of obtaining face type matching dressing scores, hair style matching facial types and facial type matching dressing scores corresponding to a plurality of face type matching dressing styles, hair style matching facial type matching dressing scores and facial type matching dressing scores corresponding to skin colors, adding the face type dressing scores, the hair style matching dressing scores and the facial type matching dressing scores corresponding to skin colors of each group to obtain a face type dressing total score, and selecting a group of corresponding face type matching dressing scores with the highest face type dressing total score as a final face type recommended dressing. Because the face shape, the hairstyle and the skin color of each user are different, the recommended scores of each set of makeup for different face shapes, hairstyles and skin colors are also different, for example, two features in the face shapes, hairstyles and skin colors obtained after two users are identified are similar, but the finally obtained makeup matching results are also different, for example, the face shapes and hairstyles are similar, but the skin colors are different, one skin color is white, one skin color is dark, the difference in the recommended scores of some makeup is quite large, and the obtained recommended results are also different.
Referring to fig. 2, features of the makeup recommendation are refined in the second embodiment based on the first embodiment, and for some users with high requirements on the overall sense of the makeup, the recommendation method of the second embodiment may be selected, so as to perform the subdivision of the makeup on the forehead, the face, the nose, the mouth and the eyes, and perform the fine makeup recommendation on the user, where the plurality of face shapes further include: several forehead contours, several face contours, several nose contours, several mouth contours and several eye contours. The face of the person mainly comprises the forehead, the nose, the mouth, the eyes and the face, so that the fine recommendation is performed on the features, and the requirements of fine matching of the makeup of the user can be met.
The several kinds of makeup looks still include: several facial matching make-up, several nose matching make-up, several mouth matching make-up and several eyes matching make-up. The memory module 11 further includes: a second score correspondence unit 112, the second score correspondence unit 112 being configured with a second score correspondence policy including: performing forehead matching dressing scores on each forehead contour, face contour, nose contour, mouth contour and eye contour respectively, and setting the forehead dressing scores, face corresponding forehead dressing scores, nose corresponding forehead dressing scores, mouth corresponding forehead dressing scores and eye corresponding forehead dressing scores respectively;
respectively carrying out face matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the face makeup score, the nose corresponding face makeup score, the mouth corresponding face makeup score and the eye corresponding face makeup score;
nose matching makeup scores are respectively carried out on each forehead outline, face outline, nose outline, mouth outline and eye outline, and the nose matching makeup scores are respectively set as a forehead corresponding nose makeup score, a face corresponding nose makeup score, a mouth corresponding nose makeup score and an eye corresponding nose makeup score;
performing mouth matching dressing scores on each forehead outline, face outline, nose outline, mouth outline and eye outline respectively, and setting the mouth matching dressing scores, face matching mouth dressing scores, nose matching mouth dressing scores, mouth dressing scores and eye matching mouth dressing scores as corresponding forehead dressing scores;
and respectively carrying out eye matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the eye matching makeup scoring, the face corresponding eye makeup scoring, the nose corresponding eye makeup scoring, the mouth corresponding eye makeup scoring and the eye makeup scoring.
The recording module 13 further comprises: a second recording unit 132, where the second recording unit 132 is used to record pictures of the face of the user. The feature extraction unit 121 is further configured to extract features in a picture of a face of a user, and the feature extraction unit 121 is further configured with a second extraction policy, where the second extraction policy includes: and extracting the forehead outline, the face outline, the nose outline, the mouth outline and the eye outline in the face picture of the user, and respectively comparing the forehead outline, the face outline, the mouth outline and the eye outline with a plurality of forehead outlines, a plurality of face outlines, a plurality of nose outlines, a plurality of mouth outlines and a plurality of eye outlines in the storage module 11 to obtain corresponding matched forehead, matched face, matched nose, matched mouth and matched eyes.
The matching unit 122 is further configured with a second matching policy, which includes: obtaining a forehead dressing score, a face corresponding forehead dressing score, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score of a plurality of forehead matching dressing scores corresponding to a matching face, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score, adding the forehead dressing score, the face corresponding forehead dressing score, the nose corresponding forehead dressing score, the mouth corresponding forehead dressing score and the eye corresponding forehead dressing score of each group of forehead dressing scores to obtain a forehead dressing total score, and selecting a group of corresponding forehead matching dressing scores with the highest forehead dressing total score as a final forehead recommended dressing score;
obtaining a forehead corresponding face dressing score, a nose corresponding face dressing score, a mouth corresponding face dressing score and an eye corresponding face dressing score of a plurality of face matching dressing scores corresponding to a matched forehead, adding the face dressing score, the nose corresponding face dressing score, the mouth corresponding face dressing score and the eye corresponding face dressing score of each group of forehead corresponding face dressing score, mouth corresponding face dressing score and eye corresponding face dressing score to obtain a face dressing total score, and selecting a group of corresponding face matching dressing scores with the highest face dressing total score as a final face recommendation dressing score;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding nose dressing score, a face corresponding nose dressing score, a mouth corresponding nose dressing score and an eye corresponding nose dressing score of a matched eye corresponding to a plurality of nose matching dressing, adding the nose dressing score, the face corresponding nose dressing score, the mouth corresponding nose dressing score and the eye corresponding nose dressing score of each group of forehead corresponding nose dressing score to obtain a nose dressing total score, and selecting a group of corresponding nose matching dressing with the highest nose dressing total score as a final nose recommendation dressing;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding mouth dressing score, a face corresponding mouth dressing score, a nose corresponding mouth dressing score, a mouth dressing score and an eye corresponding mouth dressing score of a plurality of mouth matching dressing, adding the forehead corresponding mouth dressing score, the face corresponding mouth dressing score, the nose corresponding mouth dressing score, the mouth dressing score and the eye corresponding mouth dressing score of each group to obtain a mouth dressing total score, and selecting a group of corresponding mouth matching dressing with the highest mouth dressing total score as a final mouth recommendation dressing;
the method comprises the steps of obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding eye dressing score, a face corresponding eye dressing score, a nose corresponding eye dressing score, a mouth corresponding eye dressing score and an eye dressing score of a matched eye corresponding to a plurality of eye matching dressing, adding the forehead corresponding eye dressing score, the face corresponding eye dressing score, the nose corresponding eye dressing score, the mouth corresponding eye dressing score and the eye dressing score to obtain an eye dressing total score, and selecting a group of corresponding eye matching dressing with the highest eye dressing total score as a final eye recommendation dressing.
When the forehead, the face, the nose, the mouth and the eyes are in correspondence with the makeup except the face, the corresponding score is matched, for example, when a user with a wider forehead performs nose makeup recommendation, different nose makeup can influence the overall feeling of the forehead, so that the scores of the makeup of different noses can be high or low for the user with the wider forehead, the makeup of other characteristics can be mutually influenced, and the user can select the closest final score for recommendation under the condition of relatively balanced influence, and can select from the makeup with the front score according to the needs of the user.
Working principle: after the user enters the recommendation system 1 through the user side, the whole recommendation mode or the fine recommendation mode can be selected, then the features of the face are recorded through the recording module 13, after the features are processed through the processing module 12, the pre-stored features in the storage module 11 are retrieved for comparison, then after the score of the dressing recommendation is accumulated, the dressing with high score is preferentially recommended after the score is accumulated for each set of dressing, of course, the user can also select from the dressing with the front score according to the preference, and the feasibility and the rationality of the dressing recommendation can be improved.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (4)
1. A face recognition based cosmetic recommendation system, comprising: the face pack comprises a storage module (11), a recording module (13) and a processing module (12), wherein the storage module (11) stores a plurality of facial features and a plurality of makeup types, the recording module (13) is used for recording facial image data of a user, and the processing module (12) is used for processing according to the acquired facial image data and matching a set of makeup for the user;
the several facial features include: several hairstyles, several facial forms, and several skin colors;
the several kinds of makeup looks include: several facial forms match the makeup;
the memory module (11) further comprises: a first score correspondence unit (111), the first score correspondence unit (111) being configured with a first score correspondence policy, the first score correspondence policy comprising: scoring a plurality of facial form matching makeup corresponding to each facial form, hairstyle and skin color, and setting the facial form matching makeup score, the hairstyle corresponding to the facial form matching makeup score and the skin color corresponding to the facial form matching makeup score respectively;
the admission module (13) comprises: the first recording unit (131) is used for recording the whole picture of the user;
the processing module (12) comprises: the device comprises a feature extraction unit (121) and a matching unit (122), wherein the feature extraction unit (121) is used for extracting features in a picture of the whole user, and the matching unit (122) is used for matching the makeup according to the combination of the extracted features;
the feature extraction unit (121) is configured with a first extraction strategy comprising: extracting hairstyles, facial forms and skin colors in the whole picture of the user, and comparing the hairstyles, facial forms and skin colors with a plurality of hairstyles, facial forms and skin colors in a storage module (11) to obtain corresponding matched hairstyles, matched facial forms and matched skin colors;
the matching unit (122) is configured with a first matching policy comprising: obtaining face type dressing scores of matching face types, matching hairstyles and matching skin colors corresponding to a plurality of face type matching dressing styles, matching dressing scores of hairstyles corresponding to the face types and matching dressing scores of skin colors corresponding to the face types, adding the face type dressing scores of each group of face type dressing scores, the hairstyles corresponding to the face type matching dressing scores and the face type matching dressing scores corresponding to the skin colors to obtain a face type dressing total score, and selecting a group of corresponding face type matching dressing scores with the highest face type dressing total score as a final face type recommended dressing;
the several facial features further include: several forehead contours, several face contours, several nose contours, several mouth contours, and several eye contours;
the several kinds of makeup looks still include: several forehead matching makeup, several face matching makeup, several nose matching makeup, several mouth matching makeup and several eyes matching makeup;
the memory module (11) further comprises: a second score correspondence unit (112), the second score correspondence unit (112) being configured with a second score correspondence policy, the second score correspondence policy comprising: performing forehead matching dressing scores on each forehead contour, face contour, nose contour, mouth contour and eye contour respectively, and setting the forehead dressing scores, face corresponding forehead dressing scores, nose corresponding forehead dressing scores, mouth corresponding forehead dressing scores and eye corresponding forehead dressing scores respectively;
respectively carrying out face matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the face makeup score, the nose corresponding face makeup score, the mouth corresponding face makeup score and the eye corresponding face makeup score;
nose matching makeup scores are respectively carried out on each forehead outline, face outline, nose outline, mouth outline and eye outline, and the nose matching makeup scores are respectively set as a forehead corresponding nose makeup score, a face corresponding nose makeup score, a mouth corresponding nose makeup score and an eye corresponding nose makeup score;
performing mouth matching dressing scores on each forehead outline, face outline, nose outline, mouth outline and eye outline respectively, and setting the mouth matching dressing scores, face matching mouth dressing scores, nose matching mouth dressing scores, mouth dressing scores and eye matching mouth dressing scores as corresponding forehead dressing scores;
and respectively carrying out eye matching makeup scoring on each forehead outline, face outline, nose outline, mouth outline and eye outline, and respectively setting the eye matching makeup scoring, the face corresponding eye makeup scoring, the nose corresponding eye makeup scoring, the mouth corresponding eye makeup scoring and the eye makeup scoring.
2. A makeup recommendation system based on facial recognition according to claim 1, wherein said admission module (13) further comprises: and the second recording unit (132) is used for recording pictures of the face of the user.
3. A makeup recommendation system based on facial recognition according to claim 2, wherein said feature extraction unit (121) is further configured to extract features in a picture of a user's face, said feature extraction unit (121) is further configured with a second extraction policy, said second extraction policy comprising: and extracting the forehead outline, the face outline, the nose outline, the mouth outline and the eye outline in the face picture of the user, and respectively comparing the forehead outline, the face outline, the nose outline, the mouth outline and the eye outline with a plurality of forehead outlines, a plurality of face outlines, a plurality of nose outlines, a plurality of mouth outlines and a plurality of eye outlines in the storage module (11) to obtain corresponding matched forehead, matched face, matched nose, matched mouth and matched eyes.
4. A face recognition based makeup recommendation system according to claim 3, wherein said matching unit (122) is further configured with a second matching policy comprising: obtaining a forehead dressing score, a face corresponding forehead dressing score, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score of a plurality of forehead matching dressing scores corresponding to a matching face, a mouth corresponding forehead dressing score and an eye corresponding forehead dressing score, adding the forehead dressing score, the face corresponding forehead dressing score, the nose corresponding forehead dressing score, the mouth corresponding forehead dressing score and the eye corresponding forehead dressing score of each group of forehead dressing scores to obtain a forehead dressing total score, and selecting a group of corresponding forehead matching dressing scores with the highest forehead dressing total score as a final forehead recommended dressing score;
obtaining a forehead corresponding face dressing score, a nose corresponding face dressing score, a mouth corresponding face dressing score and an eye corresponding face dressing score of a plurality of face matching dressing scores corresponding to a matched forehead, adding the face dressing score, the nose corresponding face dressing score, the mouth corresponding face dressing score and the eye corresponding face dressing score of each group of forehead corresponding face dressing score, mouth corresponding face dressing score and eye corresponding face dressing score to obtain a face dressing total score, and selecting a group of corresponding face matching dressing scores with the highest face dressing total score as a final face recommendation dressing score;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding nose dressing score, a face corresponding nose dressing score, a mouth corresponding nose dressing score and an eye corresponding nose dressing score of a matched eye corresponding to a plurality of nose matching dressing, adding the nose dressing score, the face corresponding nose dressing score, the mouth corresponding nose dressing score and the eye corresponding nose dressing score of each group of forehead corresponding nose dressing score to obtain a nose dressing total score, and selecting a group of corresponding nose matching dressing with the highest nose dressing total score as a final nose recommendation dressing;
obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding mouth dressing score, a face corresponding mouth dressing score, a nose corresponding mouth dressing score, a mouth dressing score and an eye corresponding mouth dressing score of a plurality of mouth matching dressing, adding the forehead corresponding mouth dressing score, the face corresponding mouth dressing score, the nose corresponding mouth dressing score, the mouth dressing score and the eye corresponding mouth dressing score of each group to obtain a mouth dressing total score, and selecting a group of corresponding mouth matching dressing with the highest mouth dressing total score as a final mouth recommendation dressing;
the method comprises the steps of obtaining a matched forehead, a matched face, a matched nose, a matched mouth and a forehead corresponding eye dressing score, a face corresponding eye dressing score, a nose corresponding eye dressing score, a mouth corresponding eye dressing score and an eye dressing score of a matched eye corresponding to a plurality of eye matching dressing, adding the forehead corresponding eye dressing score, the face corresponding eye dressing score, the nose corresponding eye dressing score, the mouth corresponding eye dressing score and the eye dressing score to obtain an eye dressing total score, and selecting a group of corresponding eye matching dressing with the highest eye dressing total score as a final eye recommendation dressing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110858375.1A CN113592591B (en) | 2021-07-28 | 2021-07-28 | Face recognition-based dressing recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110858375.1A CN113592591B (en) | 2021-07-28 | 2021-07-28 | Face recognition-based dressing recommendation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592591A CN113592591A (en) | 2021-11-02 |
| CN113592591B true CN113592591B (en) | 2024-02-02 |
Family
ID=78251187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110858375.1A Active CN113592591B (en) | 2021-07-28 | 2021-07-28 | Face recognition-based dressing recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592591B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08202754A (en) * | 1995-01-27 | 1996-08-09 | Pola Chem Ind Inc | Lip color advise system and method for the same |
| CN101673475A (en) * | 2009-09-15 | 2010-03-17 | 宇龙计算机通信科技(深圳)有限公司 | Method for realizing making-up guidance at terminal and equipment and system |
| CN201716740U (en) * | 2010-07-06 | 2011-01-19 | 上海慧广科技发展有限公司 | Intelligent facial recognition system |
| CN106649465A (en) * | 2016-09-26 | 2017-05-10 | 珠海格力电器股份有限公司 | Recommendation and acquisition method and device of cosmetic information |
| CN108234591A (en) * | 2017-09-21 | 2018-06-29 | 深圳市商汤科技有限公司 | The content-data of identity-based verification device recommends method, apparatus and storage medium |
| CN108345849A (en) * | 2018-01-31 | 2018-07-31 | 深圳港云科技有限公司 | A kind of face recognition method and its equipment |
| CN108536876A (en) * | 2017-03-01 | 2018-09-14 | 青岛萨纳斯智能科技股份有限公司 | The technical method of moulding makeup is carried out by face recognition based on robot |
| CN108920490A (en) * | 2018-05-14 | 2018-11-30 | 京东方科技集团股份有限公司 | Assist implementation method, device, electronic equipment and the storage medium of makeup |
| CN110020187A (en) * | 2018-05-22 | 2019-07-16 | 京东方科技集团股份有限公司 | A kind of makeup proposal recommending method, device and relevant device |
| CN110110118A (en) * | 2017-12-27 | 2019-08-09 | 广东欧珀移动通信有限公司 | Dressing recommended method, device, storage medium and mobile terminal |
| CN110197420A (en) * | 2019-06-06 | 2019-09-03 | 江西服装学院 | A kind of intelligent dressing system |
| KR20200107492A (en) * | 2019-03-08 | 2020-09-16 | 주식회사 에이아이네이션 | Apparatus for generating virtual makeup image score |
| CN111783511A (en) * | 2019-10-31 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Beauty treatment method, device, terminal and storage medium |
| KR20210004596A (en) * | 2019-07-05 | 2021-01-13 | 전재원 | Personalized color app recommendations by artificial intelligence |
| CN115544354A (en) * | 2022-09-20 | 2022-12-30 | 长城汽车股份有限公司 | Makeup assisting method and device, electronic equipment and vehicle |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9760762B2 (en) * | 2014-11-03 | 2017-09-12 | Anastasia Soare | Facial structural shaping |
-
2021
- 2021-07-28 CN CN202110858375.1A patent/CN113592591B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08202754A (en) * | 1995-01-27 | 1996-08-09 | Pola Chem Ind Inc | Lip color advise system and method for the same |
| CN101673475A (en) * | 2009-09-15 | 2010-03-17 | 宇龙计算机通信科技(深圳)有限公司 | Method for realizing making-up guidance at terminal and equipment and system |
| CN201716740U (en) * | 2010-07-06 | 2011-01-19 | 上海慧广科技发展有限公司 | Intelligent facial recognition system |
| CN106649465A (en) * | 2016-09-26 | 2017-05-10 | 珠海格力电器股份有限公司 | Recommendation and acquisition method and device of cosmetic information |
| CN108536876A (en) * | 2017-03-01 | 2018-09-14 | 青岛萨纳斯智能科技股份有限公司 | The technical method of moulding makeup is carried out by face recognition based on robot |
| CN108234591A (en) * | 2017-09-21 | 2018-06-29 | 深圳市商汤科技有限公司 | The content-data of identity-based verification device recommends method, apparatus and storage medium |
| CN110110118A (en) * | 2017-12-27 | 2019-08-09 | 广东欧珀移动通信有限公司 | Dressing recommended method, device, storage medium and mobile terminal |
| CN108345849A (en) * | 2018-01-31 | 2018-07-31 | 深圳港云科技有限公司 | A kind of face recognition method and its equipment |
| CN108920490A (en) * | 2018-05-14 | 2018-11-30 | 京东方科技集团股份有限公司 | Assist implementation method, device, electronic equipment and the storage medium of makeup |
| CN110020187A (en) * | 2018-05-22 | 2019-07-16 | 京东方科技集团股份有限公司 | A kind of makeup proposal recommending method, device and relevant device |
| KR20200107492A (en) * | 2019-03-08 | 2020-09-16 | 주식회사 에이아이네이션 | Apparatus for generating virtual makeup image score |
| CN110197420A (en) * | 2019-06-06 | 2019-09-03 | 江西服装学院 | A kind of intelligent dressing system |
| KR20210004596A (en) * | 2019-07-05 | 2021-01-13 | 전재원 | Personalized color app recommendations by artificial intelligence |
| CN111783511A (en) * | 2019-10-31 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Beauty treatment method, device, terminal and storage medium |
| CN115544354A (en) * | 2022-09-20 | 2022-12-30 | 长城汽车股份有限公司 | Makeup assisting method and device, electronic equipment and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592591A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447466B (en) | A kind of identity integrated recognition method based on Kinect sensor | |
| CN109376582A (en) | A kind of interactive human face cartoon method based on generation confrontation network | |
| CN107506559B (en) | Star face shaping makeup recommendation method and device based on face similarity analysis | |
| CN104331564B (en) | Adorn guidance method and terminal device based on terminal device | |
| CN102184108A (en) | Method for performing virtual makeup by using computer program and makeup simulation program | |
| CN109063671A (en) | Method and device for intelligent cosmetic | |
| CN111291642A (en) | Dressing method, dressing device, electronic equipment and storage medium | |
| Eckert et al. | Facial cosmetics database and impact analysis on automatic face recognition | |
| KR101987189B1 (en) | Makeup recommendation kiosk | |
| CN108460398A (en) | Image processing method, device, cloud processing equipment and computer program product | |
| D’ambra | Mode and model in the flavian female portrait | |
| US20130106900A1 (en) | Method and apparatus for generating avatar | |
| CN113592591B (en) | Face recognition-based dressing recommendation system | |
| KR101071984B1 (en) | Method for semi-permanent special make-up of eyebrows | |
| US11227424B2 (en) | Method and system to provide a computer-modified visualization of the desired face of a person | |
| Choi | Korean fashion media, beauty ideals, and colorism: Examining the prominence of whiteness between 2013 and 2017 in Céci magazine | |
| CN110930294A (en) | Intelligent hair style recommendation and presentation method | |
| Wood | Subject and Artist: Studies in Roman Portraiture of the Third Century | |
| KR102588813B1 (en) | System for recommending eyebrow treatment customized based on artificial intelligence vision verification | |
| KR101045964B1 (en) | Semi-permanent eye line special makeup method | |
| Park | Analysis of hair design formative factors in the women's one length hair style in the Imperial Japanese colonial period | |
| CN110069716A (en) | A kind of makeups recommended method, system and computer readable storage medium | |
| CN102972969A (en) | Portable eyebrow drawing device | |
| KR200425470Y1 (en) | Pad capable of making up on the part of face | |
| CN113724366B (en) | 3D model generation method, device and equipment |
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 |