CN109583426A - A method of according to image identification face - Google Patents
A method of according to image identification face Download PDFInfo
- Publication number
- CN109583426A CN109583426A CN201811576765.4A CN201811576765A CN109583426A CN 109583426 A CN109583426 A CN 109583426A CN 201811576765 A CN201811576765 A CN 201811576765A CN 109583426 A CN109583426 A CN 109583426A
- Authority
- CN
- China
- Prior art keywords
- face
- head portrait
- feature
- image
- module
- 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 21
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- 238000012790 confirmation Methods 0.000 claims abstract description 9
- 210000001938 protoplast Anatomy 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 6
- 230000014759 maintenance of location Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 7
- 230000010354 integration Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- 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)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to technical field of computer vision, a kind of more particularly to method according to image identification face, comprising the following steps: the head portrait selection of protoplast's object, low resolution picture and the conversion of high-resolution pictures, the analysis of original image, the extraction of head portrait feature and analysis, the data transmission of head portrait feature, contrast images sieve take, the analysis of contrast images, original image feature and the comparison of contrast images feature and the confirmation of personage's head portrait.Present invention employs carry out analysis modeling to the face characteristic in personage's video, and the picture of low resolution is converted into high-resolution pictures, the feature integration in picture will be compared, data comparison is carried out to the feature in character features and contrast images, conveniently recognized identity of personage information has the convenient the advantages of information of offender is inquired and confirmed, facilitates the data query to convict, the efficiency of identity information inquiry is increased, and precision is higher.
Description
Technical field
The present invention relates to technical field of computer vision, specially a kind of method according to image identification face.
Background technique
It needs to carry out screenshot to crime character image during integrating crime personage's screen information, then root
According to character image carry out signature analysis, in character image information carry out retrieval analysis, with database in people information into
Row comparison, facilitates the data information of inquiry criminal, and the existing method recognized to personage mostly uses personnel to observe greatly,
Or character image analysis, but the pictorial information resolution ratio in monitor video is lower, is difficult to personage's head portrait feature in monitoring
It extracts, is not easy to inquire the data of convict, increases the difficulty for arresting convict.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of method according to image identification face, have to monitoring
People information in video carries out feature integration, and the picture of low resolution is converted into high-resolution pictures, convenient to crime
The advantages of information of molecule is inquired and is confirmed, the data query to convict is facilitated.
In order to achieve the above object, the present invention is achieved by the following technical programs: a kind of according to image identification face
Method, comprising the following steps:
1), the head portrait selection of protoplast's object:
Head portrait interception is carried out to the target person in video in monitor video, and picture feature analysis is carried out to multiple screenshots,
It is spare.
2), the conversion of low resolution picture and high-resolution pictures:
It is standby by the identical characteristics of image of multiple low resolution using resolution adjustment software assembly at a high-resolution picture
With；
3), the analysis of original image:
Integrated full resolution pricture is imported to the inside of analytical equipment, image scanning analysis is carried out, by the head image data after analysis
It is integrated, and modeled software carries out 3D modeling, it is spare.
4), the extraction and analysis of head portrait feature:
Feature on the 3D modeling head portrait of production is extracted, face 500-600 characteristic dimension is extracted, is inserted into temporary library,
Temporarily as unit of face, interim ID is distributed as face unique identifier, is integrated with 500-600 characteristic dimension storages
Analysis, it is spare.
5), the data transmission of head portrait feature:
500-600 features of face are transferred on the end PC, the database at the end PC is imported, it is spare.
6), the sieve of contrast images takes
The image for needing to compare is shown on PC display screen, and is carried out sieve to the portrait on image and be rounded conjunction, spare.
7), the analysis of contrast images:
Face locating is carried out to the portrait that sieve takes, face 500-600 characteristic dimension is extracted, temporary library is inserted into, temporarily with face
It for unit, distributes interim ID and carries out confluence analysis with 500-600 characteristic dimension storages as face unique identifier, and is right
The feature of extraction is integrated, and is stored in data store internal, spare.
8), the comparison of original image feature and contrast images feature:
The 500-600 head portrait feature that original image is extracted, compares with 500-600 head portrait feature in documents, leads to
Face identification and comparison algorithm is crossed, temporary library is carried out and judges whether there is: if it does not, comparison face distributes interim ID, and being pushed away
Send to base library carry out face alignment, then through recognition of face alignment algorithm carry out face judgement, inquire face ID, output as a result,
If it does, can according to historical record carry out human face discriminating, if identified successfully or it is no be more than face temporarily store
Quantity is filtered duplicate and identified face, retains effective face and carries out base library comparison, spare.
9), the confirmation of personage's head portrait:
If documents head portrait feature and protoplast's object head portrait Characteristic Contrast are coincide, then personage's head portrait confirms, inquires its identity automatically
Information carries out confirmation identity.
Preferably, the end PC is desktop computer.
Preferably, the 3D modeling software in the step 3) is Maya modeling software.
Preferably, the step 2 intermediate-resolution adjustment software is RAISR.
It is a kind of according to image identification face system, including image transmission module, the output end of described image transmission module with
The input terminal of head portrait modeling module is electrically connected, the output end of the head portrait modeling module and the input terminal of head portrait characteristic extracting module
Electrical connection, the output end of the head portrait characteristic extracting module are electrically connected with the input terminal of PC；
The output end of the PC is electrically connected with the input terminal of image display, the output end and portrait of described image display module
The input terminal electrical connection of modulus block is sieved, the output end of the portrait sieve modulus block is electrically connected with the input terminal of Face detection module,
The output end of the Face detection module is electrically connected with the input terminal of face characteristic extraction module, the face characteristic extraction module
Output end be electrically connected with the input terminal of feedback module, the input of the output end of the feedback module and face characteristic contrast module
End electrical connection, the output end of the face characteristic contrast module are electrically connected with the input terminal of identity validation module.
By the above-mentioned description of this invention it is found that compared with prior art, the present invention have it is following the utility model has the advantages that
(1), present invention employs in personage's video face characteristic carry out analysis modeling, and by the picture of low resolution convert
For high-resolution pictures, the feature integration in picture will be compared, data pair are carried out to the feature in character features and contrast images
Than conveniently recognized identity of personage information has and conveniently the information of offender is inquired and confirmed, facilitates to convict
Data query the advantages of.
(2), present invention employs the method according to image identification face, can quickly to the character features in image into
Row analysis, and the image face characteristic in identity information in database is compared, the efficiency of identity information inquiry is increased,
And precision is higher.
Detailed description of the invention
Fig. 1 is system diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment one:
A method of according to image identification face, comprising the following steps:
1), the head portrait selection of protoplast's object:
Head portrait interception is carried out to the target person in video in monitor video, and picture feature analysis is carried out to multiple screenshots,
It is spare.
2), the conversion of low resolution picture and high-resolution pictures:
The identical characteristics of image of multiple low resolution is assembled into a high-resolution figure using resolution adjustment software RAISR
Piece, it is spare；
3), the analysis of original image:
Integrated full resolution pricture is imported to the inside of analytical equipment, image scanning analysis is carried out, by the head image data after analysis
It is integrated, and modeled software carries out 3D modeling, 3D modeling software is Maya modeling software, spare.
4), the extraction and analysis of head portrait feature:
Feature on the 3D modeling head portrait of production is extracted, 600 characteristic dimensions of face are extracted, is inserted into temporary library, temporarily
As unit of face, interim ID is distributed as face unique identifier, carries out confluence analysis with 600 characteristic dimension storages, it is standby
With.
5), the data transmission of head portrait feature:
600 features of face are transferred on the end PC, the end PC is desktop computer, imports the database at the end PC, spare.
6), the sieve of contrast images takes
The image for needing to compare is shown on PC display screen, and is carried out sieve to the portrait on image and be rounded conjunction, spare.
7), the analysis of contrast images:
Face locating is carried out to the portrait that sieve takes, 600 characteristic dimensions of face is extracted, is inserted into temporary library, is temporarily single with face
Position distributes interim ID and carries out confluence analysis with 600 characteristic dimension storages as face unique identifier, and to the spy of extraction
Sign is integrated, and is stored in data store internal, spare.
8), the comparison of original image feature and contrast images feature:
600 head portrait features that original image is extracted, compare with 600 head portrait features in documents, are known by face
Other alignment algorithm carries out temporary library and judges whether there is: if it does not, comparison face distributes interim ID, and pushing to basis
Library carry out face alignment, then through recognition of face alignment algorithm carry out face judgement, inquire face ID, output as a result, if it does,
Can according to historical record carry out human face discriminating, if identified successfully or it is no be more than face temporarily store quantity, weigh
Multiple and identified face is filtered, and is retained effective face and is carried out base library comparison, spare.
9), the confirmation of personage's head portrait:
If documents head portrait feature and protoplast's object head portrait Characteristic Contrast are coincide, then personage's head portrait confirms, inquires its identity automatically
Information carries out confirmation identity.
Embodiment two:
A method of according to image identification face, comprising the following steps:
1), the head portrait selection of protoplast's object:
Head portrait interception is carried out to the target person in video in monitor video, and picture feature analysis is carried out to multiple screenshots,
It is spare.
2), the conversion of low resolution picture and high-resolution pictures:
The identical characteristics of image of multiple low resolution is assembled into a high-resolution figure using resolution adjustment software RAISR
Piece, it is spare；
3), the analysis of original image:
Integrated full resolution pricture is imported to the inside of analytical equipment, image scanning analysis is carried out, by the head image data after analysis
It is integrated, and modeled software carries out 3D modeling, 3D modeling software is Maya modeling software, spare.
4), the extraction and analysis of head portrait feature:
Feature on the 3D modeling head portrait of production is extracted, 512 characteristic dimensions of face are extracted, is inserted into temporary library, temporarily
As unit of face, interim ID is distributed as face unique identifier, carries out confluence analysis with 512 characteristic dimension storages, it is standby
With.
5), the data transmission of head portrait feature:
512 features of face are transferred on the end PC, the end PC is desktop computer, imports the database at the end PC, spare.
6), the sieve of contrast images takes
The image for needing to compare is shown on PC display screen, and is carried out sieve to the portrait on image and be rounded conjunction, spare.
7), the analysis of contrast images:
Face locating is carried out to the portrait that sieve takes, 512 characteristic dimensions of face is extracted, is inserted into temporary library, is temporarily single with face
Position distributes interim ID and carries out confluence analysis with 500-600 characteristic dimension storages as face unique identifier, and to extraction
Feature integrated, and be stored in data store internal, it is spare.
8), the comparison of original image feature and contrast images feature:
512 head portrait features that original image is extracted, compare with 512 head portrait features in documents, are known by face
Other alignment algorithm carries out temporary library and judges whether there is: if it does not, comparison face distributes interim ID, and pushing to basis
Library carry out face alignment, then through recognition of face alignment algorithm carry out face judgement, inquire face ID, output as a result, if it does,
Can according to historical record carry out human face discriminating, if identified successfully or it is no be more than face temporarily store quantity, weigh
Multiple and identified face is filtered, and is retained effective face and is carried out base library comparison, spare.
9), the confirmation of personage's head portrait:
If documents head portrait feature and protoplast's object head portrait Characteristic Contrast are coincide, then personage's head portrait confirms, inquires its identity automatically
Information carries out confirmation identity.
Super-resolution technique, which refers to from the low-resolution image observed, reconstructs corresponding high-definition picture, is monitoring
There is important application value in the fields such as equipment, satellite image and medical image, and SR can be divided into two classes, from multiple low resolution figures
As reconstructing high-definition picture and reconstructing high-definition picture from single low-resolution image.The SR of deep learning, mainly
It is the method for reconstructing based on single low-resolution, i.e. SISR, SISR is that an inverse problem can for a low-resolution image
There can be many different high-definition pictures to be corresponding to it, therefore can usually add a priori when solving high-definition picture
Information carries out standardization constraint, and in traditional method, this prior information can pass through several low-high resolutions occurred in pairs
It is acquired in the example of rate image, and the SR based on deep learning directly learns image in different resolution to high-resolution by neural network
The mapping function end to end of image.
SISR is by identifying low-quality image, and then intelligence upshift, makes image appear to have the effect of high quality.Equally
Importantly, working as you on either device, even in mobile device, as long as the image of a downloading low resolution, it will be certainly
It is dynamic that it is identified, and conversion in real time occurs, generate the big figure of high definition.SISR technology need to continue on low resolution and high score
Resolution image carries out alternately testing, so that technology is more accurate.Machine learning can also make system find out the best mistake of effect
Filter rebuilds the high quality image version of low resolution picture.After largely testing, final SISR technology can be real
The high quality sampling of existing most of images, without high-resolution version as reference.
Referring to Fig. 1, the present invention provides a kind of technical solution: a kind of to be passed according to image identification face system, including image
The output end of defeated module, described image transmission module is electrically connected with the input terminal of head portrait modeling module, the head portrait modeling module
Output end be electrically connected with the input terminal of head portrait characteristic extracting module, the output end of the head portrait characteristic extracting module and PC's is defeated
Enter end electrical connection；
The output end of the PC is electrically connected with the input terminal of image display, the output end and portrait of described image display module
The input terminal electrical connection of modulus block is sieved, the output end of the portrait sieve modulus block is electrically connected with the input terminal of Face detection module,
The output end of the Face detection module is electrically connected with the input terminal of face characteristic extraction module, the face characteristic extraction module
Output end be electrically connected with the input terminal of feedback module, the input of the output end of the feedback module and face characteristic contrast module
End electrical connection, the output end of the face characteristic contrast module are electrically connected with the input terminal of identity validation module.
The invention has the benefit that present invention employs analysis modeling is carried out to the face characteristic in personage's video, and
The picture of low resolution is converted into high-resolution pictures, the feature integration in picture will be compared, to character features and comparison diagram
Feature as in carries out data comparison, and conveniently recognized identity of personage information has and conveniently looks into the information of offender
The advantages of asking and confirming, facilitate the data query to convict.
Present invention employs the methods according to image identification face, can quickly divide the character features in image
Analysis, and the image face characteristic in identity information in database is compared, increase the efficiency of identity information inquiry, and essence
Du Genggao.
The method provided by the present invention according to image identification face is described in detail above.Invention applies
A specific example illustrates the principle and implementation of the invention, and the above embodiments are only used to help understand originally
The method and its core concept of invention.It should be pointed out that for those skilled in the art, not departing from this hair
, can be with several improvements and modifications are made to the present invention under the premise of bright principle, these improvement and modification also fall into power of the present invention
In the protection scope that benefit requires.
Claims (5)
1. a kind of method according to image identification face, comprising the following steps:
1), the head portrait selection of protoplast's object:
Head portrait interception is carried out to the target person in video in monitor video, and picture feature analysis is carried out to multiple screenshots,
It is spare；
2), the conversion of low resolution picture and high-resolution pictures:
It is standby by the identical characteristics of image of multiple low resolution using resolution adjustment software assembly at a high-resolution picture
With；
3), the analysis of original image:
Integrated full resolution pricture is imported to the inside of analytical equipment, image scanning analysis is carried out, by the head image data after analysis
It is integrated, and modeled software carries out 3D modeling, it is spare；
4), the extraction and analysis of head portrait feature:
Feature on the 3D modeling head portrait of production is extracted, face 500-600 characteristic dimension is extracted, is inserted into temporary library,
Temporarily as unit of face, interim ID is distributed as face unique identifier, is integrated with 500-600 characteristic dimension storages
Analysis, it is spare；
5), the data transmission of head portrait feature:
500-600 features of face are transferred on the end PC, the database at the end PC is imported, it is spare；
6), the sieve of contrast images takes:
The image for needing to compare is shown on PC display screen, and is carried out sieve to the portrait on image and be rounded conjunction, spare；
7), the analysis of contrast images:
Face locating is carried out to the portrait that sieve takes, face 500-600 characteristic dimension is extracted, temporary library is inserted into, temporarily with face
It for unit, distributes interim ID and carries out confluence analysis with 500-600 characteristic dimension storages as face unique identifier, and is right
The feature of extraction is integrated, and is stored in data store internal, spare；
8), the comparison of original image feature and contrast images feature:
The 500-600 head portrait feature that original image is extracted, compares with 500-600 head portrait feature in documents, leads to
Face identification and comparison algorithm is crossed, temporary library is carried out and judges whether there is: if it does not, comparison face distributes interim ID, and being pushed away
Send to base library carry out face alignment, then through recognition of face alignment algorithm carry out face judgement, inquire face ID, output as a result,
If it does, can according to historical record carry out human face discriminating, if identified successfully or it is no be more than face temporarily store
Quantity is filtered duplicate and identified face, retains effective face and carries out base library comparison, spare；
9), the confirmation of personage's head portrait:
If documents head portrait feature and protoplast's object head portrait Characteristic Contrast are coincide, then personage's head portrait confirms, inquires its identity automatically
Information carries out confirmation identity.
2. a kind of method according to image identification face according to claim 1, it is characterised in that: the end PC is desk-top
Computer.
3. a kind of method according to image identification face according to claim 1, it is characterised in that: in the step 3)
3D modeling software is Maya modeling software.
4. a kind of method according to image identification face according to claim 1, it is characterised in that: divide in the step 2
It is RAISR that resolution, which adjusts software,.
5. a kind of according to image identification face system, including image transmission module, it is characterised in that: described image transmission module
Output end is electrically connected with the input terminal of head portrait modeling module, the output end and head portrait characteristic extracting module of the head portrait modeling module
Input terminal electrical connection, the output end of the head portrait characteristic extracting module is electrically connected with the input terminal of PC；
The output end of the PC is electrically connected with the input terminal of image display, the output end and portrait of described image display module
The input terminal electrical connection of modulus block is sieved, the output end of the portrait sieve modulus block is electrically connected with the input terminal of Face detection module,
The output end of the Face detection module is electrically connected with the input terminal of face characteristic extraction module, the face characteristic extraction module
Output end be electrically connected with the input terminal of feedback module, the input of the output end of the feedback module and face characteristic contrast module
End electrical connection, the output end of the face characteristic contrast module are electrically connected with the input terminal of identity validation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576765.4A CN109583426A (en) | 2018-12-23 | 2018-12-23 | A method of according to image identification face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811576765.4A CN109583426A (en) | 2018-12-23 | 2018-12-23 | A method of according to image identification face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109583426A true CN109583426A (en) | 2019-04-05 |
Family
ID=65931359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811576765.4A Pending CN109583426A (en) | 2018-12-23 | 2018-12-23 | A method of according to image identification face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583426A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188602A (en) * | 2019-04-17 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Face identification method and device in video |
| CN111241917A (en) * | 2019-12-25 | 2020-06-05 | 杭州中威电子股份有限公司 | Self-adaptive non-contact physiological acquisition holder camera device and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006074146A (en) * | 2004-08-31 | 2006-03-16 | Pentax Corp | Photographing apparatus |
| US20060187305A1 (en) * | 2002-07-01 | 2006-08-24 | Trivedi Mohan M | Digital processing of video images |
| US20070019887A1 (en) * | 2004-06-30 | 2007-01-25 | Oscar Nestares | Computing a higher resolution image from multiple lower resolution images using model-base, robust bayesian estimation |
| CN101697197A (en) * | 2009-10-20 | 2010-04-21 | 西安交通大学 | Method for recognizing human face based on typical correlation analysis spatial super-resolution |
| US20100312734A1 (en) * | 2005-10-07 | 2010-12-09 | Bernard Widrow | System and method for cognitive memory and auto-associative neural network based pattern recognition |
| CN103903236A (en) * | 2014-03-10 | 2014-07-02 | 北京信息科技大学 | Method and device for reconstructing super-resolution facial image |
| CN106815560A (en) * | 2016-12-22 | 2017-06-09 | 广州大学 | It is a kind of to be applied to the face identification method that self adaptation drives seat |
| CN107016361A (en) * | 2017-03-29 | 2017-08-04 | 成都三零凯天通信实业有限公司 | Recognition methods and device based on video analysis |
| CN107463864A (en) * | 2016-06-02 | 2017-12-12 | 国家计算机网络与信息安全管理中心 | A kind of face identification system of binding sequence image super-resolution rebuilding |
| WO2018001092A1 (en) * | 2016-06-29 | 2018-01-04 | 中兴通讯股份有限公司 | Face recognition method and apparatus |
| CN108073577A (en) * | 2016-11-08 | 2018-05-25 | 中国电信股份有限公司 | A kind of alarm method and system based on recognition of face |
-
2018
- 2018-12-23 CN CN201811576765.4A patent/CN109583426A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060187305A1 (en) * | 2002-07-01 | 2006-08-24 | Trivedi Mohan M | Digital processing of video images |
| US20070019887A1 (en) * | 2004-06-30 | 2007-01-25 | Oscar Nestares | Computing a higher resolution image from multiple lower resolution images using model-base, robust bayesian estimation |
| JP2006074146A (en) * | 2004-08-31 | 2006-03-16 | Pentax Corp | Photographing apparatus |
| US20100312734A1 (en) * | 2005-10-07 | 2010-12-09 | Bernard Widrow | System and method for cognitive memory and auto-associative neural network based pattern recognition |
| CN101697197A (en) * | 2009-10-20 | 2010-04-21 | 西安交通大学 | Method for recognizing human face based on typical correlation analysis spatial super-resolution |
| CN103903236A (en) * | 2014-03-10 | 2014-07-02 | 北京信息科技大学 | Method and device for reconstructing super-resolution facial image |
| CN107463864A (en) * | 2016-06-02 | 2017-12-12 | 国家计算机网络与信息安全管理中心 | A kind of face identification system of binding sequence image super-resolution rebuilding |
| WO2018001092A1 (en) * | 2016-06-29 | 2018-01-04 | 中兴通讯股份有限公司 | Face recognition method and apparatus |
| CN108073577A (en) * | 2016-11-08 | 2018-05-25 | 中国电信股份有限公司 | A kind of alarm method and system based on recognition of face |
| CN106815560A (en) * | 2016-12-22 | 2017-06-09 | 广州大学 | It is a kind of to be applied to the face identification method that self adaptation drives seat |
| CN107016361A (en) * | 2017-03-29 | 2017-08-04 | 成都三零凯天通信实业有限公司 | Recognition methods and device based on video analysis |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188602A (en) * | 2019-04-17 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Face identification method and device in video |
| CN111241917A (en) * | 2019-12-25 | 2020-06-05 | 杭州中威电子股份有限公司 | Self-adaptive non-contact physiological acquisition holder camera device and method |
| CN111241917B (en) * | 2019-12-25 | 2023-08-22 | 杭州中威电子股份有限公司 | Self-adaptive non-contact physiological acquisition cradle head camera device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107145900B (en) | Pedestrian based on consistency constraint feature learning recognition methods again | |
| US20140270431A1 (en) | Characterizing pathology images with statistical analysis of local neural network responses | |
| CN108537191B (en) | Three-dimensional face recognition method based on structured light camera | |
| CN110544205B (en) | Image super-resolution reconstruction method based on visible light and infrared cross input | |
| CN106559654A (en) | A kind of recognition of face monitoring collection system and its control method | |
| DE112019000334T5 (en) | VALIDATE THE IDENTITY OF A REMOTE USER BY COMPARISON ON THE BASIS OF THRESHOLD VALUES | |
| CN110135437A (en) | For the damage identification method of vehicle, device, electronic equipment and computer storage medium | |
| CN108549848B (en) | Method and apparatus for outputting information | |
| EP3940585A1 (en) | Image processing method based on artificial intelligence, microscope, system and medium | |
| CN109190588A (en) | A kind of method and device of population classification | |
| CN106227850A (en) | A kind of medical test monitoring control system based on mobile terminal and control method | |
| CN108921038A (en) | A kind of classroom based on deep learning face recognition technology is quickly called the roll method of registering | |
| CN104123556A (en) | Examinee authentication system and method based on image recognition | |
| WO2021120961A1 (en) | Brain addiction structure map evaluation method and apparatus | |
| CN109583426A (en) | A method of according to image identification face | |
| CN108388889A (en) | Method and apparatus for analyzing facial image | |
| CN110399810A (en) | A kind of auxiliary magnet name method and device | |
| CN111385530B (en) | Intelligent camera combined encryption method and system | |
| CN108090982A (en) | One kind is registered method, system and terminal device | |
| CN110473176A (en) | Image processing method and device, method for processing fundus images, electronic equipment | |
| CN107480576A (en) | Face identification method, living body faces detection method, device and equipment | |
| CN209015173U (en) | Face character automatic identification equipment based on CNN algorithm | |
| Siregar et al. | Human face recognition using eigenface in cloud computing environment | |
| CN107798312B (en) | Automatic attendance checking method based on visual head detection | |
| CN109977769A (en) | A kind of method of micro- Expression Recognition under low resolution environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |