CN106446851A - Visible light based human face optimal selection method and system - Google Patents
Visible light based human face optimal selection method and system Download PDFInfo
- Publication number
- CN106446851A CN106446851A CN201610870876.0A CN201610870876A CN106446851A CN 106446851 A CN106446851 A CN 106446851A CN 201610870876 A CN201610870876 A CN 201610870876A CN 106446851 A CN106446851 A CN 106446851A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- calculate
- score value
- score
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
The invention provides a natural light based human face optimal selection method and system. The method and system provided by the invention are combined with evaluation indexes of the human face three-dimensional rotation angle, the human face sunlight exposure area, the human face definition and the human face blocking area so as to adapt to quality evaluation of the human face in different application scenarios. In addition, images with excessive low quality are directly eliminated firstly through preprocessing so as to improve the calculation efficiency in the scoring process.
Description
Technical field
The present invention relates to technical field of image processing, particularly to a kind of face method for optimizing based on visible ray and be
System.
Background technology
Face recognition technology has been widely used for all kinds of electronic systems, such as gate control system, bayonet system, E-Passport,
Public security, bank self-help system, information security etc..But easily produce the situation of misrecognition in face recognition process, how to improve
Discrimination is just particularly important.And the facial image that a width is of high quality is identified, higher matching rate can be produced, thus
Improve face identification rate.
So that evaluating to the quality of facial image, pick out scoring highest facial image.Current image
Quality evaluating method, such as to evaluate simply by face definition, is difficult to adapt to the change of sunlight；And for example pass through face deflection angle
Degree is evaluated, and artificially blocks a certain position on the face when having, this evaluation method also lost efficacy.
Content of the invention
For this reason, the present invention proposes a kind of face method for optimizing based on visible ray and system, in conjunction with face three-dimensional rotation angle
Degree, the evaluation index of face sunlight exposure area, face definition and face shielded area, to adapt to face in different application
The quality evaluation of scene, and first pass through the pretreatment directly too low image of exclusion quality, to improve the calculating in scoring process
Efficiency.
Concrete scheme is as follows：
A kind of face method for optimizing based on visible ray, including step：
Input human face image sequence；
Face quality score is carried out to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Calculating face quality general comment score value highest image will be weighted as preferred image and export.
Further, also include the step to facial image pretreatment, after input human face image sequence step, calculate
Go out the size of face in facial image, if the size of face is more than the threshold value of a setting, enter in human face image sequence
The step that each width facial image carries out face quality score, otherwise gives up this facial image.
A kind of face optimum decision system based on visible ray, including：
Input module, for inputting human face image sequence,
Grading module, for carrying out face quality score to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Output module, as preferred image and defeated for calculating face quality general comment score value highest image will be weighted
Go out.
Further, also include pretreatment module, the step for pre-processing to facial image, in input facial image sequence
After row step, calculate the size of face in facial image, if the size of face is more than the threshold value of a setting, enter to people
The step that each width facial image in face image sequence carries out face quality score, otherwise gives up this facial image.
Compared with prior art：The present invention passes through to adapt to face in different application field with reference to multiple different evaluation indexes
The quality evaluation of scape, it is to avoid carry out the limitation of quality evaluation by single features, to reach accurate assessment facial image
Quality, and by pretreatment step first exclude the relatively low facial image of quality, to simplify the operand in scoring process, with
Improve the efficiency of scoring further.
Brief description
Fig. 1 is the flow chart of the inventive method.
Specific embodiment
For further illustrating each embodiment, the present invention is provided with accompanying drawing.These accompanying drawings are the invention discloses one of content
Point, it is mainly in order to illustrate embodiment, and can coordinate the associated description of the specification operation principles to explain embodiment.Cooperation ginseng
Examine these contents, those of ordinary skill in the art will be understood that other possible embodiments and advantages of the present invention.Now tie
The present invention is further described to close the drawings and specific embodiments.
Embodiment one
As shown in figure 1, being the method flow diagram of the embodiment of the present invention, it includes step：
Input human face image sequence；
Human face image sequence pre-processes：Calculate the size of face in facial image, if the size of face is more than the threshold of a setting
Value, then enter the step carrying out face quality score to each width facial image in human face image sequence, otherwise give up this face
Image；
Face quality score is carried out to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Calculating face quality general comment score value highest image will be weighted as preferred image and export.
In the present embodiment, human face image sequence can be gathered by cam device, before carrying out facial pretreatment, need
By Face datection algorithm, face in image is positioned, to obtain the face in a rectangle frame region, the step of pretreatment
Just face rectangle frame area can be calculated in rapid, i.e. the size of face, by setting the threshold value of a face size, filters and shoots
Hypertelorism or the not good low quality facial image of angle, to reduce the data processing amount in subsequent process.
In the present embodiment, before face quality score is carried out to each width facial image in human face image sequence, need
First human face five-sense-organ is positioned.When calculating face three-dimensional deflection angle, less with respect to the deflection angle in face front, its
The corresponding score value A obtaining is just higher.When calculating face sunlight exposure area, can first calculate the moon after face is blocked by sunlight
Shadow area, and then combine face gross area acquiring size face sunlight exposure area, sunlight exposure area is bigger, corresponding face
Brightness is also bigger, and in terms of overall range of luminance values, in interlude, its corresponding score value B is higher for brightness value, during two ends,
B is relatively low for its score value.When calculating face definition, acquisition, definition and score value C can directly be calculated by energy gradient function
It is directly proportional.Calculate face shielded area, by being different from the pixel value at other positions of face, face block surface can be calculated
Long-pending, face shielded area is bigger, and more D is lower for its score value.
In the present embodiment, face three-dimensional rotation angle, face sunlight exposure area, face definition and face block surface
Long-pending scoring weight can specifically regard neatly adjustment and obtain relatively reasonable weighted value.
Embodiment two
Based on the above-mentioned face method for optimizing based on visible ray, it is preferred that the present invention also proposes a kind of face based on visible ray
System, including：
Input module, for inputting human face image sequence,
Pretreatment module, the step for pre-processing to facial image, after input human face image sequence step, calculate people
The size of face in face image, if the size of face is more than the threshold value of a setting, enters to each width in human face image sequence
The step that facial image carries out face quality score, otherwise gives up this facial image,
Grading module, for carrying out face quality score to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Output module, as preferred image and defeated for calculating face quality general comment score value highest image will be weighted
Go out.
Although specifically show and describe the present invention in conjunction with preferred embodiment, those skilled in the art should be bright
In vain, in the spirit and scope of the present invention being limited without departing from appended claims, in the form and details can be right
The present invention makes a variety of changes, and is protection scope of the present invention.
Claims (4)
1. a kind of face method for optimizing based on visible ray is it is characterised in that include step：
Input human face image sequence；
Face quality score is carried out to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Calculating face quality general comment score value highest image will be weighted as preferred image and export.
2. the face method for optimizing based on visible ray according to claim 1 is it is characterised in that also include to facial image
The step of pretreatment, after input human face image sequence step, calculates the size of face in facial image, if face is big
The little threshold value being more than a setting, then enter the step that each width facial image in human face image sequence is carried out with face quality score
Suddenly, otherwise give up this facial image.
3. a kind of face optimum decision system based on visible ray is it is characterised in that include：
Input module, for inputting human face image sequence,
Grading module, for carrying out face quality score to each width facial image in human face image sequence：
Calculate face three-dimensional rotation angle, using face three-dimensional rotation angle as the first face quality evaluation index, score value
It is designated as A；
Calculate face sunlight exposure area, using face sunlight exposure area as the second face quality evaluation index, score value
It is designated as B；
Calculate face definition, using face definition as the 3rd face quality evaluation index, score value is designated as C；
Calculate face shielded area, using face shielded area as the 4th face quality evaluation index, score value is designated as D；
By weighted calculation face quality overall score E=a*A+b*B+c*C+d*D, wherein a, b, c, d are respectively the three-dimensional rotation of face
Gyration, the scoring weight of face sunlight exposure area, face definition and face shielded area, a+b+c+d=1,
Output module, as preferred image and defeated for calculating face quality general comment score value highest image will be weighted
Go out.
4. the face optimum decision system based on visible ray according to claim 3 is it is characterised in that also include pre-processing mould
Block, the step for pre-processing to facial image, after input human face image sequence step, calculate face in facial image
Size, if the size of face be more than one setting threshold value, enter and each width facial image in human face image sequence carried out
The step of face quality score, otherwise gives up this facial image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610870876.0A CN106446851A (en) | 2016-09-30 | 2016-09-30 | Visible light based human face optimal selection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610870876.0A CN106446851A (en) | 2016-09-30 | 2016-09-30 | Visible light based human face optimal selection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106446851A true CN106446851A (en) | 2017-02-22 |
Family
ID=58172740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610870876.0A Pending CN106446851A (en) | 2016-09-30 | 2016-09-30 | Visible light based human face optimal selection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446851A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480500A (en) * | 2017-08-11 | 2017-12-15 | 维沃移动通信有限公司 | The method and mobile terminal of a kind of face verification |
| CN108197604A (en) * | 2018-01-31 | 2018-06-22 | 上海敏识网络科技有限公司 | Fast face positioning and tracing method based on embedded device |
| CN108230293A (en) * | 2017-05-31 | 2018-06-29 | 深圳市商汤科技有限公司 | Determine method and apparatus, electronic equipment and the computer storage media of quality of human face image |
| CN109389019A (en) * | 2017-08-14 | 2019-02-26 | 杭州海康威视数字技术股份有限公司 | Facial image selection method, device and computer equipment |
| CN109711390A (en) * | 2019-01-17 | 2019-05-03 | 深圳英飞拓科技股份有限公司 | Face scratches the preferred method and device of figure picture |
| CN109816628A (en) * | 2018-12-20 | 2019-05-28 | 深圳云天励飞技术有限公司 | Face evaluation method and Related product |
| CN109902624A (en) * | 2019-02-27 | 2019-06-18 | 百度在线网络技术（北京）有限公司 | The method and apparatus of information for rendering |
| CN110147744A (en) * | 2019-05-09 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of quality of human face image appraisal procedure, device and terminal |
| CN110321843A (en) * | 2019-07-04 | 2019-10-11 | 杭州视洞科技有限公司 | A kind of face out of kilter method based on deep learning |
| CN110580808A (en) * | 2018-06-08 | 2019-12-17 | 杭州海康威视数字技术股份有限公司 | Information processing method and device, electronic equipment and intelligent traffic system |
| CN110765913A (en) * | 2019-10-15 | 2020-02-07 | 浙江大华技术股份有限公司 | Human body target optimization method and device based on multiple evaluation indexes and storage medium |
| CN110837750A (en) * | 2018-08-15 | 2020-02-25 | 华为技术有限公司 | Human face quality evaluation method and device |
| CN111179489A (en) * | 2018-11-29 | 2020-05-19 | 广东网深锐识科技有限公司 | Dynamic portrait recognition control access control and dynamic portrait recognition control method |
| CN111241927A (en) * | 2019-12-30 | 2020-06-05 | 新大陆数字技术股份有限公司 | Cascading type face image optimization method, system and equipment and readable storage medium |
| CN112990156A (en) * | 2021-05-12 | 2021-06-18 | 深圳市安软科技股份有限公司 | Optimal target capturing method and device based on video and related equipment |
| US11557147B2 (en) | 2018-08-22 | 2023-01-17 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for selecting a best facial image of a target human face |
| CN117097989A (en) * | 2023-10-18 | 2023-11-21 | 北京道仪数慧科技有限公司 | Image optimization processing method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101609500A (en) * | 2008-12-01 | 2009-12-23 | 公安部第一研究所 | Quality estimation method of exit-entry digital portrait photos |
| CN103942525A (en) * | 2013-12-27 | 2014-07-23 | 高新兴科技集团股份有限公司 | Real-time face optimal selection method based on video sequence |
| CN105120167A (en) * | 2015-08-31 | 2015-12-02 | 广州市幸福网络技术有限公司 | Certificate picture camera and certificate picture photographing method |
| CN105224921A (en) * | 2015-09-17 | 2016-01-06 | 桂林远望智能通信科技有限公司 | A kind of facial image preferentially system and disposal route |
-
2016
- 2016-09-30 CN CN201610870876.0A patent/CN106446851A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101609500A (en) * | 2008-12-01 | 2009-12-23 | 公安部第一研究所 | Quality estimation method of exit-entry digital portrait photos |
| CN103942525A (en) * | 2013-12-27 | 2014-07-23 | 高新兴科技集团股份有限公司 | Real-time face optimal selection method based on video sequence |
| CN105120167A (en) * | 2015-08-31 | 2015-12-02 | 广州市幸福网络技术有限公司 | Certificate picture camera and certificate picture photographing method |
| CN105224921A (en) * | 2015-09-17 | 2016-01-06 | 桂林远望智能通信科技有限公司 | A kind of facial image preferentially system and disposal route |
Non-Patent Citations (2)
| Title |
|---|
| 胡杨庆等: "《人脸图像质量评价法》", 《现代计算机(专业版)》 * |
| 马志强: "《彩色图像中人脸检测问题的研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018219180A1 (en) * | 2017-05-31 | 2018-12-06 | 深圳市商汤科技有限公司 | Method and apparatus for determining facial image quality, as well as electronic device and computer storage medium |
| US11182589B2 (en) | 2017-05-31 | 2021-11-23 | Shenzhen Sensetime Technology Co., Ltd. | Methods and apparatuses for determining face image quality, electronic devices, and computer storage media |
| CN108230293A (en) * | 2017-05-31 | 2018-06-29 | 深圳市商汤科技有限公司 | Determine method and apparatus, electronic equipment and the computer storage media of quality of human face image |
| CN107480500A (en) * | 2017-08-11 | 2017-12-15 | 维沃移动通信有限公司 | The method and mobile terminal of a kind of face verification |
| CN109389019A (en) * | 2017-08-14 | 2019-02-26 | 杭州海康威视数字技术股份有限公司 | Facial image selection method, device and computer equipment |
| CN109389019B (en) * | 2017-08-14 | 2021-11-05 | 杭州海康威视数字技术股份有限公司 | Face image selection method and device and computer equipment |
| CN108197604A (en) * | 2018-01-31 | 2018-06-22 | 上海敏识网络科技有限公司 | Fast face positioning and tracing method based on embedded device |
| CN110580808A (en) * | 2018-06-08 | 2019-12-17 | 杭州海康威视数字技术股份有限公司 | Information processing method and device, electronic equipment and intelligent traffic system |
| CN110580808B (en) * | 2018-06-08 | 2021-03-23 | 杭州海康威视数字技术股份有限公司 | Information processing method and device, electronic equipment and intelligent traffic system |
| CN110837750B (en) * | 2018-08-15 | 2023-11-03 | 华为技术有限公司 | Face quality evaluation method and device |
| CN110837750A (en) * | 2018-08-15 | 2020-02-25 | 华为技术有限公司 | Human face quality evaluation method and device |
| US11557147B2 (en) | 2018-08-22 | 2023-01-17 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for selecting a best facial image of a target human face |
| CN111179489A (en) * | 2018-11-29 | 2020-05-19 | 广东网深锐识科技有限公司 | Dynamic portrait recognition control access control and dynamic portrait recognition control method |
| CN109816628A (en) * | 2018-12-20 | 2019-05-28 | 深圳云天励飞技术有限公司 | Face evaluation method and Related product |
| CN109711390A (en) * | 2019-01-17 | 2019-05-03 | 深圳英飞拓科技股份有限公司 | Face scratches the preferred method and device of figure picture |
| CN109902624A (en) * | 2019-02-27 | 2019-06-18 | 百度在线网络技术（北京）有限公司 | The method and apparatus of information for rendering |
| CN110147744A (en) * | 2019-05-09 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of quality of human face image appraisal procedure, device and terminal |
| CN110147744B (en) * | 2019-05-09 | 2024-05-14 | 腾讯科技（深圳）有限公司 | Face image quality assessment method, device and terminal |
| CN110321843A (en) * | 2019-07-04 | 2019-10-11 | 杭州视洞科技有限公司 | A kind of face out of kilter method based on deep learning |
| CN110321843B (en) * | 2019-07-04 | 2021-11-09 | 杭州视洞科技有限公司 | Face optimization method based on deep learning |
| CN110765913A (en) * | 2019-10-15 | 2020-02-07 | 浙江大华技术股份有限公司 | Human body target optimization method and device based on multiple evaluation indexes and storage medium |
| CN111241927A (en) * | 2019-12-30 | 2020-06-05 | 新大陆数字技术股份有限公司 | Cascading type face image optimization method, system and equipment and readable storage medium |
| CN112990156A (en) * | 2021-05-12 | 2021-06-18 | 深圳市安软科技股份有限公司 | Optimal target capturing method and device based on video and related equipment |
| CN117097989A (en) * | 2023-10-18 | 2023-11-21 | 北京道仪数慧科技有限公司 | Image optimization processing method and device |
| CN117097989B (en) * | 2023-10-18 | 2024-01-02 | 北京道仪数慧科技有限公司 | Image optimization processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446851A (en) | Visible light based human face optimal selection method and system | |
| CN110909690B (en) | Method for detecting occluded face image based on region generation | |
| CN107403168A (en) | A kind of facial-recognition security systems | |
| CN106384117B (en) | A kind of vehicle color identification method and device | |
| CN112883902B (en) | Video detection method and device, electronic equipment and storage medium | |
| CN106203305A (en) | Human face in-vivo detection method and device | |
| CN108280822A (en) | The detection method and device of screen cut | |
| CN106548165A (en) | A kind of face identification method of the convolutional neural networks weighted based on image block | |
| CN105894655B (en) | Paper currency detection and recognition methods under complex environment based on RGB-D cameras | |
| EP3905104B1 (en) | Living body detection method and device | |
| WO2016175234A1 (en) | Color image processing method, color image processing program, and object recognition method and device | |
| CN113205057B (en) | Face living body detection method, device, equipment and storage medium | |
| CN110111316A (en) | Method and system based on eyes image identification amblyopia | |
| CN110059680A (en) | A kind of detection method of ID Card Image, device and equipment | |
| CN106127193B (en) | A kind of facial image recognition method | |
| CN108537143B (en) | A kind of face identification method and system based on key area aspect ratio pair | |
| CN107705254A (en) | A kind of urban environment appraisal procedure based on streetscape figure | |
| CN106570447A (en) | Face photo sunglass automatic removing method based on gray histogram matching | |
| CN104850853B (en) | City rapid extracting method and device | |
| CN114241522A (en) | Method, system, equipment and storage medium for field operation safety wearing identification | |
| CN110135446A (en) | Method for text detection and computer storage medium | |
| CN107944354A (en) | A kind of vehicle checking method based on deep learning | |
| CN110276831A (en) | Constructing method and device, equipment, the computer readable storage medium of threedimensional model | |
| CN111191535A (en) | Pedestrian detection model construction method based on deep learning and pedestrian detection method | |
| CN111191531A (en) | Rapid pedestrian detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |