CN106504104A - A kind of method of social activity of being made friends based on face recognition - Google Patents
A kind of method of social activity of being made friends based on face recognition Download PDFInfo
- Publication number
- CN106504104A CN106504104A CN201610957356.3A CN201610957356A CN106504104A CN 106504104 A CN106504104 A CN 106504104A CN 201610957356 A CN201610957356 A CN 201610957356A CN 106504104 A CN106504104 A CN 106504104A
- Authority
- CN
- China
- Prior art keywords
- face
- user
- friend
- social
- similarity
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000000694 effects Effects 0.000 title abstract description 6
- 239000013598 vector Substances 0.000 claims abstract description 15
- 230000001815 facial effect Effects 0.000 claims abstract description 14
- 230000009467 reduction Effects 0.000 claims abstract description 6
- 238000005516 engineering process Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 210000000216 zygoma Anatomy 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 3
- 230000000644 propagated effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004308 accommodation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 239000002245 particle Substances 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of method of social activity of being made friends based on face recognition, the main face-image by being autodyned according to user, by facial recognition techniques, identify 68 crucial point coordinates in face；Crucial point coordinates is calculated and is converted, formed face key index, be stored in structured database, as face's file point storehouse of user.Multiple indexs of face's archives are carried out with dimensionality reduction, representational field is extracted, " the eigenface vector " that can distinguish user is combined into；Similarity relatively between the eigenface vector of user, it is recommended that to user and star or the community users of his " looking like ", make them become friend.By analyzing the face-image of user, user is helped to find similar " siblings " in crowd；Similarity of the user with star is calculated, is improved propagated.Solve using ready-made api interface (such as face++ etc.) for adding new user picture to need all pictures of re -training, relatively time-consuming bothersome while the relatively low problem of the free degree.
Description
Technical field
The present invention relates to field of image recognition, and in particular to a kind of method of social activity of being made friends based on face recognition.
Background technology
User likes auto heterodyne to be dealt on social network sites so that the face-image for obtaining user is possibly realized.Used by analysis
The characteristics of image at family, searches the user of " looking like ", it is recommended that make friend.
Popular social solution：
1. location-based friend recommendation；
2. the friend recommendation based on user interest；
3. the friend recommendation based on graph theory；
4. the api interfaces such as Face++ are called, friend recommendation is carried out.
The shortcoming of prior art：
Using ready-made api interface (such as face++ etc.) for the new user picture of addition needs all pictures of re -training,
Relatively time-consuming bothersome while the free degree is relatively low.
Content of the invention
For solving above-mentioned deficiency of the prior art, it is an object of the invention to provide a kind of social based on face recognition friend-making
Method, by the face-image that autodynes according to user, carry out feature extraction, form the representative sample of user's face, compare use
Similarity between the facial eigenvectors of family, it is recommended that to the star or community users of user and his " looking like ".
The purpose of the present invention is realized using following technical proposals：
A kind of method of social activity of being made friends based on face recognition, methods described are comprised the steps：
(1) identifying user；
(2) facial characteristics is extracted and feature recognition, forms face's file point storehouse of user；
(3) Data Dimensionality Reduction；
(4) similarity algorithm is defined；
(5) user recommends.
Further, in step (1), by network operation means, encourage user to autodyne, identity is carried out for user
Identification, generates user's auto heterodyne image pattern storehouse.
Further, face-image of each sample comprising ID users and user front.
Further, the face feature of user's face, in step (2), is extracted, including face ratio, angle and face
Color, according to the face-image that user autodynes, by facial recognition techniques, identifies 68 crucial point coordinates in face；To closing
Key point coordinates is calculated and is converted, and (eyes to face length account for the long ratio of face, chin included angle cosine to form face key index
The ratio of the ratio of the ratio of value, lower jaw width and cheekbone width, eye spacing and right eye width, eye spacing and left eye width, right
Eye width accounts for same level face width ratio, and left eye width accounts for same level face width ratio, right eye tail of the eye cosine value, more than the left eye tail of the eye
The included angle cosine value of the included angle cosine value of string value, nose length-width ratio, the bridge of the nose and right nose lower edge, the bridge of the nose and left nose lower edge, face are flat
Equal color value (rgb value)), structured database is stored in, as face's file point storehouse of user.
For multiple face-image difference location feature point positions of same user, characteristic value is calculated, for corresponding
Characteristic value averaging, obtains standard face feature.
Further, in step (3), ID users and corresponding standard face feature index are put into as sample
In one database table, per one sample of behavior, a face feature field is often classified as.
Further, for the face feature field of each column is standardized according to the mode of (X-E (X))/δ, then
Principal component analysis dimensionality reduction is carried out, 5 representative facial face characteristic vectors is selected, wherein：X represents a face spy
The column vector of index field composition is levied, E (X) represents the average of X, and δ represents the standard deviation of X.
Further, in step (4), for a given sample, the phase between sample and other samples is calculated
Like degree, and generate list to be recommended；Cosine similarity algorithm：
If vector A=(A1, A2 ..., An), B=(B1, B2 ..Bn) calculates included angle cosine value
Wherein：I=1,2 ..., n；N represents index number.
Further, in step (5), for recommendation list in user, filtered plusing good friend and low-quality and used
Family, is presented to targeted customer by UI interfaces (user interface).
In order to the embodiment to disclosing some in terms of have a basic understanding, shown below is simple summary.Should
Summarized section is not extensive overview, nor will determine key/critical component or describe the protection domain of these embodiments.
Its sole purpose is to assume some concepts with simple form, in this, as the preamble of following detailed description.
Compared with immediate prior art, the excellent effect that the technical scheme of present invention offer has is：
By analyzing the face-image of user, facial characteristics is extracted, calculates the similarity between different facial characteristics vectors,
Recommended users are made friends.By analyzing the face-image of user, user is helped to find similar " siblings " in crowd；Calculate and use
Similarity of the family with star, improves propagated.Solve the main way that similitude is provided on contrast market, such as Face++.Solution
New user picture is certainly added then to need all pictures of re -training.Relatively time-consuming bothersome while the relatively low problem of the free degree.
Description of the drawings
Fig. 1 is the flow chart of the social method of being made friends based on face recognition that the present invention is provided.
Fig. 2 is the key point schematic diagram of face face detection.
Specific embodiment
Below in conjunction with the accompanying drawings the specific embodiment of the present invention is described in further detail.
The following description and drawings fully illustrate specific embodiments of the present invention, to enable those skilled in the art to
Put into practice them.Other embodiments can include structure, logic, electric, process and other changes.Embodiment
Possible change is only represented.Unless explicitly requested, otherwise individually component and function are optional, and the order for operating can be with
Change.The part of some embodiments and feature can be included in or replace part and the feature of other embodiments.This
The scope of bright embodiment includes the gamut of claims, and all obtainable equivalent of claims
Thing.Herein, these embodiments of the invention individually or generally can be represented with term " invention " that this is only
For convenience, and if in fact disclosing the invention more than, the scope for being not meant to automatically limit the application is to appoint
What single invention or inventive concept.
The present invention recommends potential user good friend according to the similarity degree of two pictures, by the face that is autodyned according to user
Image, carries out feature extraction, forms the characteristic vector of user, compares with the similarity between characteristic vector, it is recommended that to user with
The star of his " looking like " or community users, based on face recognition make friends social method flow chart as shown in figure 1, including
Following step：
(1) identifying user；
(2) facial characteristics is extracted and feature recognition, forms face's file point storehouse of user；
(3) sample is reselected；
(4) similarity algorithm is defined；
(5) user recommends.
In above-described embodiment, step (1) includes：First by operation means, encourage user to autodyne, body is carried out for user
Part identification, generates Sample Storehouse, face-image of the sample comprising ID users and several fronts.
In above-described embodiment：Step (2) includes：Using programming gimmick, face feature (ratio, size, angle, face is extracted
Color etc.), it is converted into vector.For multiple image difference location feature point positions of same user, characteristic value is calculated, for phase
The characteristic value averaging that answers, obtains standard face feature.According to the face-image that user autodynes, by facial recognition techniques,
Identify 68 crucial point coordinates in face；Crucial point coordinates is calculated and is converted, formed face key index (eyes
To the ratio that face length accounts for the long ratio of face, chin included angle cosine value, lower jaw width and cheekbone width, eye spacing and right eye width
Ratio, the ratio of eye spacing and left eye width, right eye width account for same level face width ratio, and left eye width accounts for same level face width ratio
The included angle cosine value of example, right eye tail of the eye cosine value, left eye tail of the eye cosine value, nose length-width ratio, the bridge of the nose and right nose lower edge, nose
The included angle cosine value of beam and left nose lower edge, facial average color (rgb value)), structured database is stored in, as the face of user
Portion file point storehouse；The key point schematic diagram of face face detection is as shown in Figure 2.
In above-described embodiment：Step (3) includes：ID and corresponding standard face feature are put into a number as sample
According to storehouse table, per one sample of behavior, a characteristic vector is often classified as.For each column field according to (X-E (X))/δ mode
It is standardized.Then principal component analysis dimensionality reduction is carried out, 5 representative characteristic vectors are selected.
In above-described embodiment：Step (4) includes：Define similarity algorithm.For a given sample, the sample is calculated
And the similarity between other samples, generate list to be recommended.Cosine similarity algorithm：
If vector A=(A1, A2 ..., An), B=(B1, B2 ..Bn) calculates included angle cosine value,
Wherein：I=1,2 ..., n；N represents index number.
In above-described embodiment：Step (5) includes：User in for recommendation list, is filtered (plusing good friend, low-quality
User), by UI displaying interfaces to targeted customer.
The technical field that the present invention is also possible to apply includes：
1st, face input and friend recommendation output are completed by neural network algorithm；
2nd, according to the element factor calculation image similarity such as color, shape, composition；
3rd, image background commending friends are based on.
Face-image of the technical scheme that the present invention is provided by analysis user, extracts facial characteristics, calculates different faces
Similarity between archive feature vector, it is recommended that user makes friends, should be obtained by the present invention
Facial characteristics coordinate points.
Unless otherwise specific statement, term such as process, calculate, computing, determination, show etc. can refer to one or more
Individual process or action and/or the process of computing system or similar devices, the action and/or process will be indicated as processing system
Data manipulation that physics (such as electronics) in the register or memory of system is measured and it is converted into and is similarly represented as processing system
Memory, register or other this type of informations storage, transmitting or display device in physical quantity other data.Information
Can be represented using any one of multiple different technology and method with signal.For example, in above description
Data, instruction, order, information, signal, bit, symbol and the chip for referring to can use voltage, electric current, electromagnetic wave, magnetic field or grain
Son, light field or particle or its be combined to represent.
It should be understood that the particular order or level the step of during disclosed is the example of illustrative methods.It is based on and sets
Meter preference, it should be appreciated that during the step of particular order or level can be in the feelings of the protection domain without departing from the disclosure
Rearranged under condition.Appended claim to a method gives the key element of various steps with exemplary order, and not
It is to be limited to described particular order or level.
In above-mentioned detailed description, various features are combined in single embodiment together, to simplify the disclosure.No
This open method should be construed to reflect such intention, i.e. the embodiment of theme required for protection needs clear
The more features of the feature stated in each claim to Chu.Conversely, that reflected such as appending claims
Sample, the present invention are in the state fewer than whole features of disclosed single embodiment.Therefore, appending claims is special
This is expressly incorporated in detailed description, and wherein each claim is alone as the single preferred embodiment of the present invention.
It should also be appreciated by one skilled in the art that the various illustrative box, mould with reference to the embodiments herein description
Block, circuit and algorithm steps can be implemented as electronic hardware, computer software or its combination.In order to clearly demonstrate hardware and
Interchangeability between software, is carried out around its function to various illustrative parts, frame, module, circuit and step above
It is generally described.Hardware is implemented as this function and is also implemented as software, depending on specific application and to whole
The design constraint applied by system.Those skilled in the art can be directed to each application-specific, be realized in the way of accommodation
Described function, but, this realize that decision-making should not be construed as the protection domain away from the disclosure.
Described above includes the citing of one or more embodiments.Certainly, in order to above-described embodiment is described and description portion
The all possible combination of part or method be impossible, but it will be appreciated by one of ordinary skill in the art that each enforcement
Example can do further combinations and permutations.Therefore, embodiment described herein is intended to fall into appended claims
Protection domain in all such changes, modifications and variations.Additionally, with regard to the term used in specification or claims
"comprising", the word cover mode similar to term " including ", are solved as link word just as " including, " in the claims
As releasing.Additionally, the use of any one term "or" in the specification of claims being to represent " non-exclusionism
Or ".
Finally it should be noted that：Above example is only in order to technical scheme to be described rather than a limitation, most
Pipe has been described in detail to the present invention with reference to above-described embodiment, and those of ordinary skill in the art still can be to this
Bright specific embodiment is modified or equivalent, these without departing from spirit and scope of the invention any modification or
Equivalent, within the claims for applying for the pending present invention.
Claims (9)
1. a kind of made friends social method based on face recognition, it is characterised in that methods described comprises the steps：
(1) identifying user；
(2) facial characteristics is extracted and feature recognition, forms face's file point storehouse of user；
(3) Data Dimensionality Reduction；
(4) similarity algorithm is defined；
(5) user recommends.
2., as claimed in claim 1 based on the method that face recognition friend-making is social, it is characterised in that in step (1), lead to
Network operation means are crossed, and are encouraged user to autodyne, identification are carried out for user, generate user's auto heterodyne image pattern storehouse.
3. as claimed in claim 2 based on the method that face recognition friend-making is social, it is characterised in that each sample includes user
No. ID and the face-image in user front.
4. as claimed in claim 1 based on the method that face recognition friend-making is social, it is characterised in that in step (2), carry
The face feature of user's face is taken, including face ratio, angle and color；According to the face-image that user autodynes, by face
Technology of identification, identifies 68 crucial point coordinates in face；Crucial point coordinates is calculated and is converted, formed face crucial
Index, is stored in structured database, used as face's file point storehouse of user.
5. as claimed in claim 4 based on the method that face recognition friend-making is social, it is characterised in that the face key index
Including：Eyes account for the ratio of the long ratio of face, chin included angle cosine value, lower jaw width and cheekbone width, eye spacing to face length
With the ratio of the ratio of right eye width, eye spacing and left eye width, right eye width accounts for same level face width ratio, left eye width account for
The folder of horizontal face width ratio, right eye tail of the eye cosine value, left eye tail of the eye cosine value, nose length-width ratio, the bridge of the nose and right nose lower edge
The included angle cosine value of angle cosine value, the bridge of the nose and left nose lower edge, facial average color, i.e. rgb value.
6. as claimed in claim 1 based on the method that face recognition friend-making is social, it is characterised in that in step (3), will
The data of ID users and corresponding standard face feature are put in a database table as sample, per one sample of behavior,
A face characteristic index field is often classified as.
7. as claimed in claim 6 based on the method that face recognition friend-making is social, it is characterised in that for the face spy of each column
Levy field to be standardized according to the mode of (X-E (X))/δ, then carry out principal component analysis dimensionality reduction, select representative 5
Individual row variable, wherein：X represents the column vector of a face characteristic index field composition, and E (X) represents the average of X, and δ is represented
The standard deviation of X.
8. as claimed in claim 1 based on the method that face recognition friend-making is social, it is characterised in that in step (4), right
In a given sample, according to cosine similarity, the similarity between sample and other samples is calculated, and generates row to be recommended
Table；
The formula of similarity is as follows：
Cosine similarity algorithm：If similarity vector A=(A1, A2 ..., An), B=(B1, B2 ..Bn) calculates included angle cosine
Value：
Wherein：I=1,2 ..., n；N represents index number.
9. as claimed in claim 1 based on the method that face recognition friend-making is social, it is characterised in that in step (5), right
User in recommendation list, is filtered plusing good friend and low-quality user, by UI displaying interfaces to targeted customer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610957356.3A CN106504104A (en) | 2016-10-27 | 2016-10-27 | A kind of method of social activity of being made friends based on face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610957356.3A CN106504104A (en) | 2016-10-27 | 2016-10-27 | A kind of method of social activity of being made friends based on face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106504104A true CN106504104A (en) | 2017-03-15 |
Family
ID=58321433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610957356.3A Pending CN106504104A (en) | 2016-10-27 | 2016-10-27 | A kind of method of social activity of being made friends based on face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106504104A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563897A (en) * | 2017-09-08 | 2018-01-09 | 廖海斌 | Based on face matching famous person pursue a goal with determination recommendation and social networks method for building up and system |
| CN108021672A (en) * | 2017-12-06 | 2018-05-11 | 北京奇虎科技有限公司 | Social recommendation method, apparatus and computing device based on photograph album |
| CN108038496A (en) * | 2017-12-04 | 2018-05-15 | 华南师范大学 | Love and marriage object matching data processing method, device, computer equipment and storage medium based on big data and deep learning |
| CN108595628A (en) * | 2018-04-24 | 2018-09-28 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109635138A (en) * | 2018-10-30 | 2019-04-16 | 厦门市杜若科技有限公司 | A kind of social networks method for building up and system based on similar appearance |
| CN109657133A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Friend-making object recommendation method, apparatus, equipment and storage medium |
| CN110147486A (en) * | 2017-10-16 | 2019-08-20 | 中国电信股份有限公司 | Friend recommendation method and apparatus |
| CN110719324A (en) * | 2019-09-30 | 2020-01-21 | 上海掌门科技有限公司 | Information pushing method and equipment |
| CN111209490A (en) * | 2020-04-24 | 2020-05-29 | 深圳市爱聊科技有限公司 | Friend-making recommendation method based on user information, electronic device and storage medium |
| CN112800885A (en) * | 2021-01-16 | 2021-05-14 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN113689604A (en) * | 2021-08-26 | 2021-11-23 | 重庆工程学院 | Access control system based on living body identification and detection method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344914A (en) * | 2007-07-09 | 2009-01-14 | 上海耀明仪表控制有限公司 | Human face recognition method based on characteristic point |
| CN103632136A (en) * | 2013-11-11 | 2014-03-12 | 北京天诚盛业科技有限公司 | Method and device for locating human eyes |
-
2016
- 2016-10-27 CN CN201610957356.3A patent/CN106504104A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344914A (en) * | 2007-07-09 | 2009-01-14 | 上海耀明仪表控制有限公司 | Human face recognition method based on characteristic point |
| CN103632136A (en) * | 2013-11-11 | 2014-03-12 | 北京天诚盛业科技有限公司 | Method and device for locating human eyes |
Non-Patent Citations (1)
| Title |
|---|
| QQQ5553321: "交友速配-人脸识别项目", 《道客巴巴：HTTP://WWW.DOC88.COM/P-3147684235897.HTML》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563897A (en) * | 2017-09-08 | 2018-01-09 | 廖海斌 | Based on face matching famous person pursue a goal with determination recommendation and social networks method for building up and system |
| CN110147486A (en) * | 2017-10-16 | 2019-08-20 | 中国电信股份有限公司 | Friend recommendation method and apparatus |
| CN110147486B (en) * | 2017-10-16 | 2021-10-29 | 中国电信股份有限公司 | Friend recommendation method and device |
| CN108038496A (en) * | 2017-12-04 | 2018-05-15 | 华南师范大学 | Love and marriage object matching data processing method, device, computer equipment and storage medium based on big data and deep learning |
| CN108021672A (en) * | 2017-12-06 | 2018-05-11 | 北京奇虎科技有限公司 | Social recommendation method, apparatus and computing device based on photograph album |
| CN108595628A (en) * | 2018-04-24 | 2018-09-28 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109635138A (en) * | 2018-10-30 | 2019-04-16 | 厦门市杜若科技有限公司 | A kind of social networks method for building up and system based on similar appearance |
| CN109657133A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Friend-making object recommendation method, apparatus, equipment and storage medium |
| CN110719324A (en) * | 2019-09-30 | 2020-01-21 | 上海掌门科技有限公司 | Information pushing method and equipment |
| CN111209490A (en) * | 2020-04-24 | 2020-05-29 | 深圳市爱聊科技有限公司 | Friend-making recommendation method based on user information, electronic device and storage medium |
| CN112800885A (en) * | 2021-01-16 | 2021-05-14 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN112800885B (en) * | 2021-01-16 | 2023-09-26 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN113689604A (en) * | 2021-08-26 | 2021-11-23 | 重庆工程学院 | Access control system based on living body identification and detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106504104A (en) | A kind of method of social activity of being made friends based on face recognition | |
| CN108197532B (en) | The method, apparatus and computer installation of recognition of face | |
| US10726244B2 (en) | Method and apparatus detecting a target | |
| US9721183B2 (en) | Intelligent determination of aesthetic preferences based on user history and properties | |
| US10719693B2 (en) | Method and apparatus for outputting information of object relationship | |
| CN108229330A (en) | Face fusion recognition methods and device, electronic equipment and storage medium | |
| CN105184304B (en) | Image identification device and characteristic quantity data register method to image identification device | |
| US20140177952A1 (en) | Color name determination device, color name determination method, information recording medium, and program | |
| CN108229296A (en) | The recognition methods of face skin attribute and device, electronic equipment, storage medium | |
| CN106898026A (en) | The dominant hue extracting method and device of a kind of picture | |
| CN105426810B (en) | Information processing unit and method for amending image | |
| CN111652315B (en) | Model training method, object classification device, electronic equipment and storage medium | |
| Bouchet et al. | Fuzzy mathematical morphology for color images defined by fuzzy preference relations | |
| CN110135389A (en) | Face character recognition methods and device | |
| Huo et al. | Semisupervised learning based on a novel iterative optimization model for saliency detection | |
| CN107392191B (en) | Method for judging identity, device and electronic equipment | |
| Xue et al. | Feature design for aesthetic inference on photos with faces | |
| CN112200844A (en) | Method, device, electronic equipment and medium for generating image | |
| US20180349681A1 (en) | Ensuring a desired distribution of content in a multimedia document for different demographic groups utilizing demographic information | |
| Lienhard et al. | How to predict the global instantaneous feeling induced by a facial picture? | |
| CN111161789B (en) | Analysis method and device for key areas of model prediction | |
| CN108921138A (en) | Method and apparatus for generating information | |
| CN110431838A (en) | The method and system of the dynamic content of recognition of face video camera are provided | |
| CN112016621A (en) | Training method of classification model, color classification method and electronic equipment | |
| CN113850748A (en) | Point cloud quality evaluation system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |