CN105046217A - Face recognition large data amount concurrency scheme processing method - Google Patents
Face recognition large data amount concurrency scheme processing method Download PDFInfo
- Publication number
- CN105046217A CN105046217A CN201510396980.6A CN201510396980A CN105046217A CN 105046217 A CN105046217 A CN 105046217A CN 201510396980 A CN201510396980 A CN 201510396980A CN 105046217 A CN105046217 A CN 105046217A
- Authority
- CN
- China
- Prior art keywords
- face
- information
- video stream
- recognition
- image
- 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
Classifications
-
- 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
Abstract
The present invention discloses a face recognition large data amount concurrency scheme processing method which comprises the steps of (a) obtaining image or video stream information by front-end optical equipment (b) detecting whether face information exists in the image or video stream information, (c) separating a face from the face information, (d) carrying out basic coding on the separated face to obtain a series of feature codes, (e) carrying out classification, calibration, dimension reduction, 3D modeling and other related technologies on the feature codes to regenerate a face information characteristic value, (f) searching the feature information in the face database through a hashing algorithm and comparing the feature information and current information to obtain a most similar face value, and (g) returning a corresponding result to the front-end equipment.
Description
Technical field
The present invention relates to the concurrent scheme disposal route of a kind of recognition of face big data quantity.
Background technology
Face technology enters domestic existing time more than ten years, application is only limitted to security protection and field under the lines such as finance always, along with Internet era arrival, a lot of company also attempts face technology to be combined with internet, thus realizes remote human face identification, also really has company to release similar product on line, but speed of development is slower, reason is, cannot provide very large online concurrency, also higher to the requirement of server.Current face recognition application field, is mainly divided into two kinds of patterns, and one is pattern under traditional line, and the advantage of this pattern is that discrimination is high, and defect is high cost, and recognition speed is slow, cannot trans-regional online layout; Two is patterns on pure line, and advantage is with low cost, and defect is that the bit error rate is high, and reaction velocity is slow.
Summary of the invention
For above-mentioned technical matters, the present invention discloses the concurrent scheme disposal route of a kind of recognition of face big data quantity, comprises the step of following recognition of face: a, front-end optical equipment obtain image or Video stream information; B, from image or Video stream information, detect whether there is face information; C, by face from wherein separating; D, the face separated is carried out some basic codings, obtain series of features code; E, by eigenwert through the correlation technique such as classification, calibration, dimensionality reduction, 3D modeling, regenerate face information eigenwert; F, by Hash scheduling algorithm retrieval face database in characteristic information, compare with current, obtain the most close face value; G, return accordingly result to front-end equipment.
The invention has the beneficial effects as follows that described recognition of face big data quantity concurrent scheme disposal route solves the interconnected networking of face recognition technology, too rely on the network bandwidth, the problem excessive to server stress; Combine line to reach the standard grade lower two kinds of patterns, make it the advantage both possessing both, abandoned again both defects, and do optimization of further upgrading on this basis, make it really can walk out laboratory environment, serve the general public; Face system is increased greatly in the range of application of all trades and professions, and changes the concurrent problem of the insurmountable large quantity of conventional face's system, can use on a large scale in actual applications.
Accompanying drawing explanation
Fig. 1 is traditional face recognition scheme figure;
Fig. 2 is the schematic diagram of the concurrent scheme disposal route of recognition of face big data quantity of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail, can implement according to this with reference to instructions word to make those skilled in the art.
As shown in the figure, the present invention discloses the concurrent scheme disposal route of a kind of recognition of face big data quantity, comprises the step of following recognition of face: a, front-end optical equipment obtain image or Video stream information; B, from image or Video stream information, detect whether there is face information; C, by face from wherein separating; D, the face separated is carried out some basic codings, obtain series of features code; E, by eigenwert through the correlation technique such as classification, calibration, dimensionality reduction, 3D modeling, regenerate face information eigenwert; F, by Hash scheduling algorithm retrieval face database in characteristic information, compare with current, obtain the most close face value; G, return accordingly result to front-end equipment.Described recognition of face big data quantity concurrent scheme disposal route solves the interconnected networking of face recognition technology, too relies on the network bandwidth, the problem excessive to server stress; Combine line to reach the standard grade lower two kinds of patterns, make it the advantage both possessing both, abandoned again both defects, and do optimization of further upgrading on this basis, make it really can walk out laboratory environment, serve the general public; Face system is increased greatly in the range of application of all trades and professions, and changes the concurrent problem of the insurmountable large quantity of conventional face's system, can use on a large scale in actual applications.
Although embodiment of the present invention are open as above, but it is not restricted to listed in instructions and embodiment utilization, it can be applied to various applicable the field of the invention completely, for those skilled in the art, can easily realize other amendment, therefore do not deviating under the universal that claim and equivalency range limit, the present invention is not limited to specific details and illustrates here and the legend described.
Claims (1)
1. the concurrent scheme disposal route of recognition of face big data quantity, is characterized in that: the step comprising following recognition of face:
A, front-end optical equipment obtain image or Video stream information;
B, from image or Video stream information, detect whether there is face information;
C, by face from wherein separating;
D, the face separated is carried out some basic codings, obtain series of features code;
E, by eigenwert through the correlation technique such as classification, calibration, dimensionality reduction, 3D modeling, regenerate face information eigenwert;
F, by Hash scheduling algorithm retrieval face database in characteristic information, compare with current, obtain the most close face value;
G, return accordingly result to front-end equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510396980.6A CN105046217A (en) | 2015-07-06 | 2015-07-06 | Face recognition large data amount concurrency scheme processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510396980.6A CN105046217A (en) | 2015-07-06 | 2015-07-06 | Face recognition large data amount concurrency scheme processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105046217A true CN105046217A (en) | 2015-11-11 |
Family
ID=54452746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510396980.6A Pending CN105046217A (en) | 2015-07-06 | 2015-07-06 | Face recognition large data amount concurrency scheme processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105046217A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469048A (en) * | 2015-11-24 | 2016-04-06 | 山东超越数控电子有限公司 | Method of increasing face detection performance |
CN108038462A (en) * | 2017-12-22 | 2018-05-15 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to real-time video and is identified |
CN108052915A (en) * | 2017-12-22 | 2018-05-18 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to video and is identified |
-
2015
- 2015-07-06 CN CN201510396980.6A patent/CN105046217A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469048A (en) * | 2015-11-24 | 2016-04-06 | 山东超越数控电子有限公司 | Method of increasing face detection performance |
CN108038462A (en) * | 2017-12-22 | 2018-05-15 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to real-time video and is identified |
CN108052915A (en) * | 2017-12-22 | 2018-05-18 | 深圳英飞拓科技股份有限公司 | A kind of method and device that Face datection is carried out to video and is identified |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101826099B (en) | Method and system for identifying similar documents and determining document diffusance | |
CN102750339B (en) | Positioning method of repeated fragments based on video reconstruction | |
CN103336957A (en) | Network coderivative video detection method based on spatial-temporal characteristics | |
CN103577423A (en) | Keyword classification method and system | |
JP2015512095A (en) | Method, apparatus and computer readable recording medium for image management in an image database | |
CN103257992A (en) | Method and system for retrieving similar videos | |
CN104834717A (en) | Web information automatic extraction method based on webpage clustering | |
CN104090882B (en) | A kind of quick clustering method of advertisement order and system, server | |
CN101807208A (en) | Method for quickly retrieving video fingerprints | |
CN105808709A (en) | Quick retrieval method and device of face recognition | |
CN104133868B (en) | A kind of strategy integrated for the classification of vertical reptile data | |
CN110969517B (en) | Bidding life cycle association method, system, storage medium and computer equipment | |
CN102902826A (en) | Quick image retrieval method based on reference image indexes | |
CN105046217A (en) | Face recognition large data amount concurrency scheme processing method | |
CN104252507A (en) | Enterprise data matching method and device | |
CN105678244B (en) | A kind of near video search method based on improved edit-distance | |
CN112650858A (en) | Method and device for acquiring emergency assistance information, computer equipment and medium | |
US9524354B2 (en) | Device, method, and program for processing data with tree structure | |
CN105790967A (en) | Weblog processing method and device | |
CN102262682B (en) | Based on the rapid attribute reduction of rough classification knowledge discovery | |
CN116975340A (en) | Information retrieval method, apparatus, device, program product, and storage medium | |
CN107657067B (en) | Cosine distance-based leading-edge scientific and technological information rapid pushing method and system | |
CN107992590B (en) | Big data system beneficial to information comparison | |
CN113886547A (en) | Client real-time conversation switching method and device based on artificial intelligence and electronic equipment | |
CN108009233B (en) | Image restoration method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151111 |
|
WD01 | Invention patent application deemed withdrawn after publication |