CN106997447A - Face identification system and face identification method - Google Patents
Face identification system and face identification method Download PDFInfo
- Publication number
- CN106997447A CN106997447A CN201610042384.2A CN201610042384A CN106997447A CN 106997447 A CN106997447 A CN 106997447A CN 201610042384 A CN201610042384 A CN 201610042384A CN 106997447 A CN106997447 A CN 106997447A
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- module
- displacement
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of face identification system, including:One camera module, takes in recognition of face information, and the recognition of face information bank of feed-in rear end is compared and identified whether as targeted customer；One Feature point recognition module, for detecting facial image and positioning facial key feature points；One displacement exports module, displacement and azimuth for exporting the single-lens image-forming component；One distance calculates module, utilizes the depth distance of the yardstick and the displacement of the human face characteristic point, calculating human face characteristic point；One recognition of face module, for comparing the depth distance of face different characteristic point, and determines whether targeted customer.The present invention further provides a kind of face identification method using above-mentioned face identification system.
Description
Technical field
The present invention relates to a kind of face identification system and face identification method, more particularly, to a kind of face identification system and face identification method that face is recognized using single-lens image data.
Background technology
Recognition of face, is a kind of biological identification technology that the facial feature information based on people carries out identification.Image or video containing face with video camera or camera collection, and automatic detect and track face in the picture, and then a series of correlation techniques of face are carried out to the face detected, generally also referred to as Identification of Images, face recognition.
Maturation and the raising of Social Agree with its technology, recognition of face is used in many fields, for example, recognition of face access control and attendance system, recognition of face antitheft door, face recognition mobile telephone unblock, and recognition of face is come robot for running etc..In recent years, in the evolution of face recognition technology, occur in that the deceptive practices of face, facial image is for example printed to paper, or use projection, LCDs (LiquidCrystalDisplay, abbreviation LCD) etc. playback equipment be shown on screen, it is positioned over before the harvester of face identification system, various facial images can be obtained, these facial images have very big similitude with real facial image, easily it is identified by system as real face, as the unsafe factor in face identification system.However, in face identification system, particularly unattended or high security occasion, it is very important using face prosthese fraud system to prevent people.Therefore, true and false recognition of face how is carried out in face recognition technology as one of current research topic.
Carry out measurement distance using the special requirement camera lens such as many camera lenses or RGBD, and then to identify whether true man's face or plane picture, but said system is costly, and be not suitable for that many camera lenses or the RGBD equipment such as mobile phone are installed, can not also use said system.
The content of the invention
In view of this, it is necessory to provide a kind of that face is recognized using single-lens image data, lower-cost face identification system and face identification method.
A kind of face identification system, including:One camera module, takes in recognition of face information, and the recognition of face information bank of feed-in rear end is compared and identified whether as targeted customer；One Feature point recognition module, for detecting facial image and positioning facial key feature points, after pretreatment, the recognizer of feed-in rear end, recognizer completes the extraction of human face characteristic point；One displacement exports module, for exporting displacement and azimuth of the single-lens image-forming component when diverse location point takes in recognition of face information；One distance calculates module, and displacement and azimuth, calculating human face characteristic point that the human face characteristic point provided by the Feature point recognition module and displacement output module are exported take in the depth distance of the connecting line of the different two positions points of recognition of face information to the single-lens image-forming component；One recognition of face module, for comparing the depth distance of face different characteristic point, and determines whether targeted customer.
The camera module includes single-lens image-forming component, for filmed image.
The Feature point recognition module obtains human face characteristic point by scale invariant feature conversion calculus method.
The displacement output module includes gyroscope and with the displacement detection module for measuring displacement sensor.
A kind of face identification method, comprises the following steps：First position recognition of face information is obtained using camera module, this is acquired into recognition of face information and is compared with the recognition of face information in recognition of face information bank, is identified whether as targeted customer, in this way, the shooting of the single-lens image-forming component progress second place；It is such as no, it is judged as that non-targeted user terminates recognition of face；Identical characteristic point is obtained from the first image and the second image by scale invariant feature conversion calculus method with Feature point recognition module, and then determines the target signature point of measuring and calculating, and distance described in feed-in calculates module；Module, which is exported, using a displacement provides distance calculating module described in the first position and the distance of the second place and azimuth feed-in that the single-lens image-forming component shot；The distance calculates the human face characteristic point that is provided by the Feature point recognition module of module and the displacement exports displacement that module exported and azimuth, calculates human face characteristic point to the first position and the depth distance of the connecting line of the second place, compare the depth distance of face different characteristic point, difference such as the depth distance of face different characteristic point is zero, is judged as that non-targeted user terminates recognition of face；Difference such as the depth distance of face different characteristic point is not zero, then judges that difference number whether in the range of receiving, in this way, is judged as that targeted customer terminates recognition of face with difference；It is such as no, it is judged as that non-targeted user terminates recognition of face.
First position recognition of face information is obtained, is compared with the recognition of face information in recognition of face information bank, second place recognition of face information is obtained and is realized by a camera module.
The displacement output module is included with the displacement detection module for measuring displacement sensor, and induction monitoring obtains the displacement that single-lens image-forming component is moved to the second place by first position.
The displacement output module includes the fixed value positioning module that instruction is shot in specified location, the first position that single-lens image-forming component is shot is the fixed position preset with the second place, and the displacement output module, which sends instruction, during shooting makes single-lens image-forming component be shot respectively with the second place in fixed first position.
Displacement output module further comprises gyroscope, can measure the camera site of first image and the azimuth of the camera site of the second image and azimuthal change when mobile device is subsequently walked.
Distance described in the displacement fixed value feed-in that the displacement output module will be stored in it calculates module.
Compared with prior art, the face identification system and face identification method that the present invention is provided can obtain face depth distance data using the scale invariant feature conversion calculus law technology of single-lens image data and maturation, recognition of face leak can be corrected by comparing, and then improves safe coefficient.In addition, face identification system is simple, cost easy to operate is relatively low, and in the equipment such as mobile phone that can be also suitably used for installing many camera lenses or RGBD, application is wider.
Brief description of the drawings
Fig. 1 is the schematic diagram of face identification system provided in an embodiment of the present invention.
Fig. 2 is the application schematic diagram of the scale invariant feature conversion calculus method of face identification system provided in an embodiment of the present invention.
Fig. 3 is the fundamental diagram of face identification system provided in an embodiment of the present invention.
Fig. 4 is the flow chart of face identification method provided in an embodiment of the present invention.
Main element symbol description
| Face identification system | 1 |
| Camera module | 10 |
| Feature point recognition module | 20 |
| Displacement exports module | 30 |
| Distance calculates module | 40 |
| Recognition of face module | 50 |
Following embodiment will further illustrate the present invention with reference to above-mentioned accompanying drawing.
Embodiment
Below in conjunction with the accompanying drawings and the specific embodiments, the face identification system and face identification method provided the present invention is described in further detail.
Referring to Fig. 1, face identification system 1 provided in an embodiment of the present invention, including a camera module 10, Feature point recognition module 20, displacement output module 30, distance calculate module 40 and recognition of face module 50.The camera module 10 takes in recognition of face information, and the recognition of face information bank of feed-in rear end is compared and identified whether as targeted customer.The Feature point recognition module 20 is used to detect facial image and position facial key feature points, after pretreatment, and the recognizer of feed-in rear end, recognizer completes the extraction of human face characteristic point.The displacement output module 30 is used to export displacement and azimuth of the camera module 10 when diverse location point takes in recognition of face information.The distance calculating module 40 leads to the displacement exported according to the human face characteristic point information and displacement output module 30 of the Feature point recognition module 20 offer and azimuth, calculates human face characteristic point to the depth distance of the connecting line of the different two positions points of the camera module 10 income recognition of face information.The recognition of face module 50 is used for the depth distance for comparing face different characteristic point, and determines whether targeted customer.
Specifically, also referring to Fig. 2 and Fig. 3, the camera module 10, which includes single-lens image-forming component, is used for filmed image.Shot using the single-lens image-forming component in a certain position and obtain the first image, the single-lens image-forming component displacement certain distance is shot again and obtains the second image, the camera site Q that the measurement of module 30 obtained or provided first image is exported by the displacement1With the camera site Q of second image2The distance between C and camera site Q1、Q2Azimuth angle alpha1、α2、β1、β2.Simultaneously, scale invariant feature conversion calculus method (Scale Invarlance Feature Transform are passed through by the Feature point recognition module 20, SIFT identical characteristic point m, m ' etc. on face) are found from the first image and the second image, and then determine it is follow-up it is calculative be on earth which characteristic point M of face depth distance, identical characteristic point m on face is found in the first image and the second image on SIFT technologies, m ' technology repeats for known techniques are not therefore excessive herein.By the camera site Q of first image1With the camera site Q of second image2The distance between C, and azimuth angle alpha1、α2、β1、β2It is fed into the distance and calculates module 40, the distance calculates module 40 and goes out human face characteristic point m using above-mentioned numerical computations1To with the above-mentioned vertical range H apart from the corresponding straight lines of C1, human face characteristic point m can also be referred to as1Depth distance, human face characteristic point m2To with the above-mentioned vertical range H apart from the corresponding straight lines of C2, human face characteristic point m can also be referred to as2Depth distance.The recognition of face module 50 is by H1, H2And the more H obtained by the above method3, H4..., therefore, by the depth distance H of face different characteristic point1, H2, H3, H4... calculating difference is compared, it is plane picture that targeted customer is can determine whether when difference is zero.Determine whether whether difference (or error, refer to further illustrate if error) in the reasonable scope and then determines whether real face when difference is not zero.
Human face characteristic point m described here1、m2And the m analogized3, m4... wait can be face nose, eyes, face, the organ such as ear.First image and second image can be that obtained image is shot in two unknown different positions now, the camera site Q of first image1With the camera site Q of second image2The distance between C can by with measure displacement sensor displacement detection module be obtained to detect, the camera site Q of first image1With the camera site Q of the second image2Azimuth can be by gyroscope (Gyro) it is known that azimuthal change when the autonomous mobile apparatus is subsequently walked can be estimated through mathematical prediction pattern on this basis.If, when not possessing measurement displacement sensor and gyroscope using the equipment of the face identification system 1, then by the camera site Q of first image1To the camera site Q of second image2It is set as fixed value to be shot, now pre-define a fixed position, and then spacing between the fixed position and azimuth by the displacement export module 30 export the numerical value to the distance calculate module 40 can or the displacement export module 30 and can send instruction in specified location and shoot first image and second image.
For example by taking mobile phone as an example, it can be shot using the camera lens of mobile phone and obtain image data, the camera site Q for the first image that follow shot is obtained is obtained using the GPS in mobile phone1With the camera site Q of the second image2The distance between C, the camera site Q for the first image that follow shot is obtained is obtained using the Gyro in mobile phone1With the camera site Q of the second image2Azimuth.
Referring to Fig. 3, the method for carrying out recognition of face using above-mentioned face identification system 1 comprises the following steps:
Step S11:The first image information is obtained using camera module 10, first image information acquired is compared with the recognition of face information in recognition of face information bank, identify whether as targeted customer, in this way, single-lens image-forming component carries out the shooting of another location, obtains the second image information；It is such as no, it is judged as that non-targeted user terminates recognition of face；
Step S12:Find the identical characteristic point on face from the first image and the second image by scale invariant feature conversion calculus method with Feature point recognition module 20, and then determine the target signature point of measuring and calculating, and distance described in feed-in calculates module 40；
Step S13:Distance and azimuth that module 30 provides first position that the single-lens image-forming component shot and the second place, distance calculating module 40 described in feed-in are exported using a displacement；
Step S14:The distance calculates the human face target characteristic point information that is provided by the Feature point recognition module 20 of module 40 and the displacement exports displacement that module 30 exported and azimuth, calculates human face characteristic point to the first position and the depth distance of the connecting line of the second place；
Step S15:The depth distance that module 40 further compares face different characteristic point is calculated using the distance, the difference of such as depth distance of face different characteristic point is zero, is judged as that non-targeted user terminates recognition of face；Difference such as the depth distance of face different characteristic point is not zero, then judges that difference number whether in the range of receiving, in this way, is judged as that targeted customer terminates recognition of face with difference；It is such as no, it is judged as that non-targeted user terminates recognition of face.
In the step S11, shot using the single-lens image-forming component in the camera module 10 in a certain position and obtain first position Q1First image at place, and then the camera module 10 obtains a certain face information, and by the recognition of face information bank of the face information feed-in rear end, be compared and identify whether as targeted customer；In this way, the camera module 10, which sends instruction, makes single-lens image-forming component carry out second place Q2The shooting at place obtains the second image；It is such as no, it is judged as that non-targeted user terminates recognition of face.Be stored with the image data of targeted customer in the recognition of face information bank, judgement in the step S11 simply needs to confirm whether the first image is identical with the image data for the targeted customer that is stored with the recognition of face information bank, be used only to compare herein whether be face identification information library storage targeted customer be it is consistent just, be not intended to judge whether targeted customer is plane picture or face of real solid etc..
In the step S12, utilize more ripe technology scale invariant feature conversion calculus method, identical characteristic point is obtained from the first image and the second image, distance described in feed-in calculates module 40, and then determines subsequently calculative is the depth distance of which characteristic point of face on earth；
In the step S13, the displacement output module 30 can be that the single-lens image-forming component is in different first position Q with the displacement detection module for measuring displacement sensor1With second place Q2It can be detected when being shot and obtain first position Q1With second place Q2The distance between C, this calculates module 40 by displacement output module 30 apart from distance described in C feed-ins；The displacement output module 30 can also export the fixed value positioning module that module or instruction are shot in specified location for fixed value, now generally do not possess measurement displacement sensor using the equipment of the face identification system 1, user can only arrive predetermined position and shoot obtaining the first image Q1With the second image Q2, in addition, displacement output module 30, which can also have, can send instruction so that the single-lens image-forming component in the camera module 10 shoots the first image Q in specified location1And the second image Q2。
In the step S14, the distance calculates the human face characteristic point m that module 40 takes in the determination by the step S12 and step S13 outputs1、m2And the camera site Q of first image1With the camera site Q of second image2The distance between C, camera site Q1With camera site Q2Azimuth angle alpha1、α2、β1、β2, and calculate human face characteristic point m1To with the above-mentioned vertical range H apart from the corresponding straight lines of C1, human face characteristic point m2To with the above-mentioned vertical range H apart from the corresponding straight lines of C2。
In the step S15, the depth distance H of face different characteristic point is compared1, H2And the more H obtained by the above method3, H4..., if face different characteristic point m1、m2... the depth distance H1, H2... difference be zero, then be judged as that non-targeted user terminates recognition of face；If face different characteristic point m1、m2... the depth distance H1, H2... difference be not zero, then judge that difference number and difference whether in the range of receiving, in this way, are judged as that targeted customer terminates recognition of face；It is such as no, it is judged as that non-targeted user terminates recognition of face.Whether what is judged herein is that targeted customer is for judging whether targeted customer is plane picture or real three-dimensional facial.
Face identification system and face identification method that the present invention is provided, it is that can obtain face depth distance data using the scale invariant feature conversion calculus law technology of single-lens image data and maturation, recognition of face leak can be corrected by comparing, and then improves safe coefficient.In addition, face identification system is simple, cost easy to operate is relatively low, and in the equipment such as mobile phone that can be also suitably used for installing many camera lenses or RGBD, application is wider.
In addition, those skilled in the art can also do other changes in spirit of the invention, these changes done according to present invention spirit should be all included in scope of the present invention.
Claims (10)
1. a kind of face identification system, including:
One camera module, takes in recognition of face information, and the recognition of face information bank of feed-in rear end is compared and identified whether as targeted customer；
One Feature point recognition module, for detecting facial image and positioning facial key feature points, after pretreatment, the recognizer of feed-in rear end, recognizer completes the extraction of human face characteristic point；
One displacement exports module, for exporting displacement and azimuth of the single-lens image-forming component when diverse location point takes in recognition of face information；
One distance calculates module, and displacement and azimuth, calculating human face characteristic point that the human face characteristic point provided by the Feature point recognition module and displacement output module are exported take in the depth distance of the connecting line of the different two positions points of recognition of face information to the single-lens image-forming component；
One recognition of face module, for comparing the depth distance of face different characteristic point, and determines whether targeted customer.
2. face identification system as claimed in claim 1, it is characterised in that the camera module includes single-lens image-forming component, for filmed image.
3. face identification system as claimed in claim 1, it is characterised in that the Feature point recognition module obtains human face characteristic point by scale invariant feature conversion calculus method.
4. face identification system as claimed in claim 1, it is characterised in that the displacement output module includes gyroscope and with the displacement detection module for measuring displacement sensor.
5. a kind of face identification method, comprises the following steps：
First position recognition of face information is obtained using camera module, this is acquired into recognition of face information and is compared with the recognition of face information in recognition of face information bank, is identified whether as targeted customer, in this way, the shooting of the single-lens image-forming component progress second place；It is such as no, it is judged as that non-targeted user terminates recognition of face；
Identical characteristic point is obtained from the first image and the second image by scale invariant feature conversion calculus method with Feature point recognition module, and then determines the target signature point of measuring and calculating, and distance described in feed-in calculates module；
Module, which is exported, using a displacement provides distance calculating module described in the first position and the distance of the second place and azimuth feed-in that the single-lens image-forming component shot；
The distance calculates the human face characteristic point that is provided by the Feature point recognition module of module and the displacement exports displacement that module exported and azimuth, calculates human face characteristic point to the first position and the depth distance of the connecting line of the second place, compare the depth distance of face different characteristic point, difference such as the depth distance of face different characteristic point is zero, is judged as that non-targeted user terminates recognition of face；Difference such as the depth distance of face different characteristic point is not zero, then judges that difference number whether in the range of receiving, in this way, is judged as that targeted customer terminates recognition of face with difference；It is such as no, it is judged as that non-targeted user terminates recognition of face.
6. face identification method as claimed in claim 5, it is characterised in that obtain first position recognition of face information, be compared with the recognition of face information in recognition of face information bank, obtains second place recognition of face information and is realized by a camera module.
7. face identification method as claimed in claim 5, it is characterised in that the displacement output module is included with the displacement detection module for measuring displacement sensor, and induction monitoring obtains the displacement that single-lens image-forming component is moved to the second place by first position.
8. face identification method as claimed in claim 5, it is characterized in that, the displacement output module includes the fixed value positioning module that instruction is shot in specified location, the first position that single-lens image-forming component is shot is the fixed position preset with the second place, and the displacement output module, which sends instruction, during shooting makes single-lens image-forming component be shot respectively with the second place in fixed first position.
9. face identification method as claimed in claim 7 or 8, it is characterized in that, displacement output module further comprises gyroscope, can measure the camera site of first image and the azimuth of the camera site of the second image and azimuthal change when mobile device is subsequently walked.
10. face identification method as claimed in claim 8, it is characterised in that distance described in the displacement fixed value feed-in that the displacement output module will be stored in it calculates module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610042384.2A CN106997447A (en) | 2016-01-22 | 2016-01-22 | Face identification system and face identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610042384.2A CN106997447A (en) | 2016-01-22 | 2016-01-22 | Face identification system and face identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106997447A true CN106997447A (en) | 2017-08-01 |
Family
ID=59428131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610042384.2A Pending CN106997447A (en) | 2016-01-22 | 2016-01-22 | Face identification system and face identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106997447A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563338A (en) * | 2017-09-12 | 2018-01-09 | 广东欧珀移动通信有限公司 | Method for detecting human face and Related product |
| CN109002793A (en) * | 2018-07-13 | 2018-12-14 | 苏州海星宝智能科技有限公司 | A kind of face identification method of intelligence sales terminal |
| CN109190528A (en) * | 2018-08-21 | 2019-01-11 | 厦门美图之家科技有限公司 | Biopsy method and device |
| CN109214310A (en) * | 2018-08-16 | 2019-01-15 | 安徽超清科技股份有限公司 | Improve the method and face identification system of recognition of face efficiency |
| CN110188604A (en) * | 2019-04-18 | 2019-08-30 | 盎锐（上海）信息科技有限公司 | Face identification method and device based on 2D and 3D image |
| CN110825765A (en) * | 2019-10-23 | 2020-02-21 | 中国建设银行股份有限公司 | Face recognition method and device |
| CN111046810A (en) * | 2019-12-17 | 2020-04-21 | 联想(北京)有限公司 | Data processing method and processing device |
| CN113128356A (en) * | 2021-03-29 | 2021-07-16 | 成都理工大学工程技术学院 | Smart city monitoring system based on image recognition |
-
2016
- 2016-01-22 CN CN201610042384.2A patent/CN106997447A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563338A (en) * | 2017-09-12 | 2018-01-09 | 广东欧珀移动通信有限公司 | Method for detecting human face and Related product |
| CN109002793A (en) * | 2018-07-13 | 2018-12-14 | 苏州海星宝智能科技有限公司 | A kind of face identification method of intelligence sales terminal |
| CN109214310A (en) * | 2018-08-16 | 2019-01-15 | 安徽超清科技股份有限公司 | Improve the method and face identification system of recognition of face efficiency |
| CN109190528A (en) * | 2018-08-21 | 2019-01-11 | 厦门美图之家科技有限公司 | Biopsy method and device |
| CN109190528B (en) * | 2018-08-21 | 2021-11-30 | 厦门美图之家科技有限公司 | Living body detection method and device |
| CN110188604A (en) * | 2019-04-18 | 2019-08-30 | 盎锐（上海）信息科技有限公司 | Face identification method and device based on 2D and 3D image |
| CN110825765A (en) * | 2019-10-23 | 2020-02-21 | 中国建设银行股份有限公司 | Face recognition method and device |
| CN111046810A (en) * | 2019-12-17 | 2020-04-21 | 联想(北京)有限公司 | Data processing method and processing device |
| CN113128356A (en) * | 2021-03-29 | 2021-07-16 | 成都理工大学工程技术学院 | Smart city monitoring system based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106997447A (en) | Face identification system and face identification method | |
| CN107545241B (en) | Neural network model training and living body detection method, device and storage medium | |
| TW201727537A (en) | Face recognition system and face recognition method | |
| CN106920279B (en) | Three-dimensional map construction method and device | |
| WO2020253010A1 (en) | Method and apparatus for positioning parking entrance in parking positioning, and vehicle-mounted terminal | |
| CN110672111B (en) | Vehicle driving path planning method, device, system, medium and equipment | |
| US10645668B2 (en) | Indoor positioning system and method based on geomagnetic signals in combination with computer vision | |
| CN108388879A (en) | Mesh object detection method, device and storage medium | |
| US20180121713A1 (en) | Systems and methods for verifying a face | |
| CN109141453A (en) | A kind of route guiding method and system | |
| CN109583505A (en) | A kind of object correlating method, device, equipment and the medium of multisensor | |
| CN108304801B (en) | Anti-cheating face recognition method, storage medium and face recognition device | |
| US10659680B2 (en) | Method of processing object in image and apparatus for same | |
| WO2016070300A1 (en) | System and method for detecting genuine user | |
| US11410461B2 (en) | Information processing system, method for managing object to be authenticated, and program | |
| CN113420682A (en) | Target detection method and device in vehicle-road cooperation and road side equipment | |
| CN108710841A (en) | A kind of face living body detection device and method based on MEMs infrared sensor arrays | |
| CN106470478A (en) | A kind of location data processing method, device and system | |
| CN112862640A (en) | Digital school zone cloud platform management system | |
| CN113673288A (en) | Idle parking space detection method and device, computer equipment and storage medium | |
| CN116311650A (en) | Man-machine interaction method based on intelligent entrance guard's sight tracking and gesture recognition | |
| CN112883809B (en) | Target detection method, device, equipment and medium | |
| WO2021090743A1 (en) | Authentication device, authentication system, authentication method, and recording medium | |
| CN112578338B (en) | Sound source positioning method, device, equipment and storage medium | |
| CN111368624A (en) | Loop detection method and device based on generation of countermeasure network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170801 |