CN112597901B - Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging - Google Patents
Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging Download PDFInfo
- Publication number
- CN112597901B CN112597901B CN202011546669.2A CN202011546669A CN112597901B CN 112597901 B CN112597901 B CN 112597901B CN 202011546669 A CN202011546669 A CN 202011546669A CN 112597901 B CN112597901 B CN 112597901B
- Authority
- CN
- China
- Prior art keywords
- face
- target
- data
- effective
- dimensional
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 210000001508 eye Anatomy 0.000 claims description 8
- 210000000214 mouth Anatomy 0.000 claims description 4
- 210000001331 nose Anatomy 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 239000000835 fiber Substances 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening 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
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a device and a method for effectively recognizing human face scenes based on three-dimensional ranging, wherein the human face recognition device comprises a camera, a multi-human face recognition module and an effective human face pickup module; the camera collects and inputs face RGB images and face depth data in front of a screen, the multi-face recognition module obtains corresponding face depth data according to the face RGB images input by the camera, the effective face pickup module calculates three-dimensional distances between face targets and a screen center point according to the face depth data returned by the multi-face recognition module, screens out face targets closest to the screen center point, and carries out face payment by taking the face targets as effective face targets. The advantages are that: the method can solve the problem that the conventional 3D camera can not identify the effective face in the multi-face scene, can rapidly identify the effective face object in the multi-face scene, realizes an efficient payment process, and enhances the customer experience.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to an effective multi-face scene face recognition device and method based on three-dimensional ranging.
Background
The face recognition technology is more and more popular, and the existing camera recognition technology is widely applied to the fields of payment, authentication and the like, but no effective screening method aiming at a multi-face scene exists at present.
Disclosure of Invention
The invention aims to provide an effective face recognition device and method for a multi-face scene based on three-dimensional ranging, so as to solve the problems in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an effective face recognition device of a multi-face scene based on three-dimensional ranging comprises,
a camera; the face depth data acquisition module is used for acquiring a face RGB image and face depth data of a current scene;
a multi-face recognition module; the face detection device is used for circularly detecting face RGB images and face depth data input by the camera; when detecting that a plurality of face targets exist in the current scene, identifying whether each face target is available face data according to the face RGB image and the face depth data;
an effective face pickup module; the method comprises the steps of establishing a coordinate system by taking a screen center point of a camera as a three-dimensional coordinate starting point, and marking each face target returned by a multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data; and respectively calculating the distance between the corresponding face target and the starting point of the three-dimensional coordinates according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance as effective face data.
S4, respectively calculating the distance between the corresponding face target and the three-dimensional coordinate starting point according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance as effective face data
The invention also aims to provide a three-dimensional ranging-based multi-face scene effective face recognition method, which is realized by using the face recognition device; the face recognition method comprises the following steps,
s1, circularly acquiring face RGB images and face depth data of a current scene input by a camera;
s2, circularly detecting face RGB images and face depth data of a current scene by a multi-face recognition module, and identifying whether each face target is available face data according to the face RGB images and the face depth data when detecting that a plurality of face targets exist in the current scene; if each face target is available face data, entering S3; otherwise, repeating the step S1;
s3, the effective face picking module establishes a coordinate system by taking a screen center point of the camera as a three-dimensional coordinate starting point, and marks each face target returned by the multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data;
s4, respectively calculating the distance between the corresponding face target and the three-dimensional coordinate starting point according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance between the face target and the three-dimensional coordinate starting point as effective face data;
s5, carrying out corresponding business processes according to the effective face data returned by the face picking module.
Preferably, the distance between each face object and the three-dimensional coordinate starting point is calculated in a manner that,
FCM dist ＝sqrt{(X 0 -FCM x ) 2 +(Y 0 -FCM y ) 2 +(Z 0 -FCM z ) 2 }
FCX dist ＝min(FC1 dist ，FC2 dist ，FC3 dist ，…，FCN dist )
wherein the FCM dist For the distance between the mth face object and the three-dimensional coordinate origin, m=1, 2,3,..n; (X) 0 ，Y 0 ，Z 0 ) Coordinates that are the starting point; (FCM) x ，FCM y ，FCM z ) The three-dimensional coordinates of the Mth face target; FCX (fiber reinforced X) dist Is effective face data.
Preferably, in the step S2, the process of judging whether the face target is available face data is that whether the face target is available face data is judged according to the characteristics of eyes, mouths and noses, wherein the process comprises two eyeball center points, four eye corner points, the middle point of two nostrils and two mouth corner points; if the face target has all the points, the face target is indicated to be available face data.
The beneficial effects of the invention are as follows: the method can solve the problem that the conventional 3D camera can not identify the effective face in the multi-face scene, can rapidly identify the effective face object in the multi-face scene, realizes an efficient payment flow, enhances customer experience, and can be applied to face identification fields of various industries such as financial payment, wine points, markets, security and the like.
Drawings
Fig. 1 is a schematic structural diagram of a face recognition device according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a face recognition method in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description is presented by way of example only and is not intended to limit the invention.
As shown in fig. 1, in this embodiment, there is provided a multi-face scene effective face recognition apparatus based on three-dimensional ranging, including,
a camera; the face depth data acquisition module is used for acquiring a face RGB image and face depth data of a current scene;
a multi-face recognition module; the face detection device is used for circularly detecting face RGB images and face depth data input by the camera; when detecting that a plurality of face targets exist in the current scene, identifying whether each face target is available face data according to the face RGB image and the face depth data;
an effective face pickup module; the method comprises the steps of establishing a coordinate system by taking a screen center point of a camera as a three-dimensional coordinate starting point, and marking each face target returned by a multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data; and respectively calculating the distance between the corresponding face target and the starting point of the three-dimensional coordinates according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance as effective face data.
S4, respectively calculating the distance between the corresponding face target and the three-dimensional coordinate starting point according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance as effective face data.
In this embodiment, the effective face recognition device specifically includes a host system and a camera connected to the host system; the host system is provided with a multi-face recognition module and an effective face pickup module, and face recognition application for calling the multi-face recognition module and the effective face pickup module to work is also arranged.
The working process of the face recognition device is as follows: the host system starts face recognition application, the camera collects face RGB images and face depth data in front of the screen and inputs the face RGB images and face depth data, the multi-face recognition module obtains corresponding face depth data according to the face RGB images input by the camera, the effective face pickup module calculates three-dimensional distances between face targets and the center point of the screen according to the face depth data returned by the multi-face recognition module, screens out face targets closest to the center point of the screen, takes the face targets as effective face targets to carry out face payment, and if not, the multi-face recognition process is carried out again.
In this embodiment, the camera is a 3D camera.
In this embodiment, the multi-face recognition module can perform definition, angle, expression and other judgment according to the face RGB image and the face depth data fed back by the 3D camera, perform clear face data snapshot, and acquire corresponding face depth data.
Example two
In the embodiment, a multi-face scene effective face recognition method based on three-dimensional ranging is provided, and the face recognition method is realized by using the face recognition device; the face recognition method comprises the following steps,
s1, circularly acquiring face RGB images and face depth data of a current scene input by a camera;
s2, circularly detecting face RGB images and face depth data of a current scene by a multi-face recognition module, and identifying whether each face target is available face data according to the face RGB images and the face depth data when detecting that a plurality of face targets exist in the current scene; if each face target is available face data, entering S3; otherwise, repeating the step S1;
s3, the effective face picking module establishes a coordinate system by taking a screen center point of the camera as a three-dimensional coordinate starting point, and marks each face target returned by the multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data;
s4, respectively calculating the distance between the corresponding face target and the three-dimensional coordinate starting point according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance between the face target and the three-dimensional coordinate starting point as effective face data;
s5, carrying out corresponding business processes according to the effective face data returned by the face picking module.
In this embodiment, the step S2 of determining whether the face target is available face data includes determining whether the face target is available face data according to characteristics of eyes, mouth and nose, wherein the face data includes two eyeball center points, four eye corner points, a midpoint of two nostrils and two mouth corner points; if the face target has all the points, the face target is indicated to be available face data.
In this embodiment, if only one face target exists in the current scene, it is also required to identify whether the face target is available face data, if so, the face target is read and a corresponding service program is entered; otherwise, re-identifying.
In this embodiment, the distance between each face object and the three-dimensional coordinate starting point is calculated by,
FCM dist ＝sqrt{(X 0 -FCM x ) 2 +(Y 0 -FCM y ) 2 +(Z 0 -FCM z ) 2 }
FCX dist ＝min(FC1 dist ，FC2 dist ，FC3 dist ，…，FCN dist )
wherein the FCM dist For the distance between the mth face object and the three-dimensional coordinate origin, m=1, 2,3,..n; (X) 0 ，Y 0 ，Z 0 ) Coordinates that are the starting point; (FCM) x ，FCM y ，FCM z ) The three-dimensional coordinates of the Mth face target; FCX (fiber reinforced X) dist Is effective face data.
By adopting the technical scheme disclosed by the invention, the following beneficial effects are obtained:
the invention provides a device and a method for effectively recognizing human face in a multi-human face scene based on three-dimensional ranging; the method can solve the problem that the conventional 3D camera can not identify the effective face in the multi-face scene, can rapidly identify the effective face object in the multi-face scene, realizes an efficient payment flow, enhances customer experience, and can be applied to face identification fields of various industries such as financial payment, wine points, markets, security and the like.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which is also intended to be covered by the present invention.
Claims (3)
1. Effective face recognition device of many face scene based on three-dimensional range finding, its characterized in that: comprising the steps of (a) a step of,
a camera; the face depth data acquisition module is used for acquiring a face RGB image and face depth data of a current scene;
a multi-face recognition module; the face detection device is used for circularly detecting face RGB images and face depth data input by the camera; when detecting that a plurality of face targets exist in the current scene, identifying whether each face target is available face data according to the face RGB image and the face depth data;
the process of judging whether the face target is available face data is that whether the face target is available face data is judged according to the characteristics of eyes, mouths and noses, wherein the face data comprises two eyeball center points, four eye corner points, the middle point of two nostrils and two mouth corner points; if the face target has all the points, the face target is indicated to be available face data;
an effective face pickup module; the method comprises the steps of establishing a coordinate system by taking a screen center point of a camera as a three-dimensional coordinate starting point, and marking each face target returned by a multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data; and respectively calculating the distance between the corresponding face target and the starting point of the three-dimensional coordinates according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance as effective face data.
2. A multi-face scene effective face recognition method based on three-dimensional ranging is characterized in that: the face recognition method is realized by using the face recognition device of claim 1; the face recognition method comprises the following steps,
s1, circularly acquiring face RGB images and face depth data of a current scene input by a camera;
s2, circularly detecting face RGB images and face depth data of a current scene by a multi-face recognition module, and identifying whether each face target is available face data according to the face RGB images and the face depth data when detecting that a plurality of face targets exist in the current scene; if each face target is available face data, entering S3; otherwise, repeating the step S1;
in the step S2, whether the face target is available face data is judged according to the characteristics of eyes, mouths and noses, wherein the face target comprises two eyeball center points, four eye corner points, the middle point of two nostrils and two mouth corner points; if the face target has all the points, the face target is indicated to be available face data;
s3, the effective face picking module establishes a coordinate system by taking a screen center point of the camera as a three-dimensional coordinate starting point, and marks each face target returned by the multi-face recognition module; sequentially marking three-dimensional coordinates of each face target according to the face depth data;
s4, respectively calculating the distance between the corresponding face target and the three-dimensional coordinate starting point according to the three-dimensional coordinates of each face target, and selecting the face target with the shortest distance between the face target and the three-dimensional coordinate starting point as effective face data;
s5, carrying out corresponding business processes according to the effective face data returned by the face picking module.
3. The three-dimensional ranging-based multi-face scene effective face recognition method of claim 2, wherein the method comprises the following steps: the distance between each face object and the three-dimensional coordinate starting point is calculated in a manner that,
FCX dist ＝min(FC1 dist ,FC2 dist ,FC3 dist ,…，FCN dist )
wherein the FCM dist Is the firstM distance between face object and three-dimensional coordinates start point, m=1, 2,3, … N; (X) 0 ,Y 0 ,Z 0 ) Coordinates that are the starting point; (FCM) x ,FCM y ,FCM z ) Three-dimensional coordinates of an Mth face target; FCX (fiber reinforced X) dist Is effective face data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011546669.2A CN112597901B (en) | 2020-12-23 | 2020-12-23 | Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011546669.2A CN112597901B (en) | 2020-12-23 | 2020-12-23 | Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112597901A CN112597901A (en) | 2021-04-02 |
| CN112597901B true CN112597901B (en) | 2023-12-29 |
Family
ID=75200777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011546669.2A Active CN112597901B (en) | 2020-12-23 | 2020-12-23 | Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597901B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362540A (en) * | 2021-06-11 | 2021-09-07 | 江苏苏云信息科技有限公司 | Traffic ticket business processing device, system and method based on multimode interaction |
| CN115641635B (en) * | 2022-11-08 | 2023-04-28 | 北京万里红科技有限公司 | Method for determining focusing parameters of iris image acquisition module and iris focusing equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110020720A (en) * | 2009-08-24 | 2011-03-03 | 삼성전자주식회사 | 3 dimension face capturing apparatus and method thereof |
| CN102054291A (en) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | Method and device for reconstructing three-dimensional face based on single face image |
| KR101438011B1 (en) * | 2013-11-08 | 2014-09-04 | 수원대학교산학협력단 | Three-dimensional face recognition system using 3d scanner |
| CN104751140A (en) * | 2015-03-30 | 2015-07-01 | 常州大学 | Three-dimensional face recognition algorithm based on deep learning SDAE theory and application thereof in field of finance |
| CN106156740A (en) * | 2016-07-05 | 2016-11-23 | 张宁 | Civil Aviation Airport terminal face system for rapidly identifying |
| CN108154550A (en) * | 2017-11-29 | 2018-06-12 | 深圳奥比中光科技有限公司 | Face real-time three-dimensional method for reconstructing based on RGBD cameras |
| CN109558815A (en) * | 2018-11-16 | 2019-04-02 | 恒安嘉新（北京）科技股份公司 | A kind of detection of real time multi-human face and tracking |
| CN109829436A (en) * | 2019-02-02 | 2019-05-31 | 福州大学 | Multi-face tracking method based on depth appearance characteristics and self-adaptive aggregation network |
| CN110852310A (en) * | 2020-01-14 | 2020-02-28 | 长沙小钴科技有限公司 | Three-dimensional face recognition method and device, terminal equipment and computer readable medium |
| CN111881841A (en) * | 2020-07-30 | 2020-11-03 | 河海大学常州校区 | Face detection and recognition method based on binocular vision |
-
2020
- 2020-12-23 CN CN202011546669.2A patent/CN112597901B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110020720A (en) * | 2009-08-24 | 2011-03-03 | 삼성전자주식회사 | 3 dimension face capturing apparatus and method thereof |
| CN102054291A (en) * | 2009-11-04 | 2011-05-11 | 厦门市美亚柏科信息股份有限公司 | Method and device for reconstructing three-dimensional face based on single face image |
| KR101438011B1 (en) * | 2013-11-08 | 2014-09-04 | 수원대학교산학협력단 | Three-dimensional face recognition system using 3d scanner |
| CN104751140A (en) * | 2015-03-30 | 2015-07-01 | 常州大学 | Three-dimensional face recognition algorithm based on deep learning SDAE theory and application thereof in field of finance |
| CN106156740A (en) * | 2016-07-05 | 2016-11-23 | 张宁 | Civil Aviation Airport terminal face system for rapidly identifying |
| CN108154550A (en) * | 2017-11-29 | 2018-06-12 | 深圳奥比中光科技有限公司 | Face real-time three-dimensional method for reconstructing based on RGBD cameras |
| CN109558815A (en) * | 2018-11-16 | 2019-04-02 | 恒安嘉新（北京）科技股份公司 | A kind of detection of real time multi-human face and tracking |
| CN109829436A (en) * | 2019-02-02 | 2019-05-31 | 福州大学 | Multi-face tracking method based on depth appearance characteristics and self-adaptive aggregation network |
| CN110852310A (en) * | 2020-01-14 | 2020-02-28 | 长沙小钴科技有限公司 | Three-dimensional face recognition method and device, terminal equipment and computer readable medium |
| CN111881841A (en) * | 2020-07-30 | 2020-11-03 | 河海大学常州校区 | Face detection and recognition method based on binocular vision |
Non-Patent Citations (1)
| Title |
|---|
| 一种抗姿态与表情变化的三维人脸识别方法;蔡川丽;张建平;张彦博;;应用光学(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112597901A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112597901B (en) | Device and method for effectively recognizing human face in multiple human face scenes based on three-dimensional ranging | |
| CN113313097B (en) | Face recognition method, terminal and computer readable storage medium | |
| CN112287866A (en) | Human body action recognition method and device based on human body key points | |
| CN110443245B (en) | License plate region positioning method, device and equipment in non-limited scene | |
| CN111191582B (en) | Three-dimensional target detection method, detection device, terminal device and computer readable storage medium | |
| CN108304801B (en) | Anti-cheating face recognition method, storage medium and face recognition device | |
| CN112287867A (en) | Multi-camera human body action recognition method and device | |
| CN112115939A (en) | Vehicle license plate recognition method and device | |
| CN110675442A (en) | Local stereo matching method and system combined with target identification technology | |
| CN114511592A (en) | Personnel trajectory tracking method and system based on RGBD camera and BIM system | |
| CN109840453B (en) | Face matching method and device | |
| CN111860498B (en) | Method, device and storage medium for generating antagonism sample of license plate | |
| CN109089102A (en) | A kind of robotic article method for identifying and classifying and system based on binocular vision | |
| CN110909568A (en) | Image detection method, apparatus, electronic device, and medium for face recognition | |
| CN112183148A (en) | Batch bar code positioning method and identification system | |
| CN112184544B (en) | Image stitching method and device | |
| CN111767839A (en) | Vehicle driving track determining method, device, equipment and medium | |
| JPH07287764A (en) | Stereoscopic method and solid recognition device using the method | |
| CN113840135B (en) | Color cast detection method, device, equipment and storage medium | |
| CN113688680B (en) | Intelligent recognition and tracking system | |
| CN115840550A (en) | Angle-adaptive display screen display method, device and medium | |
| CN114724111A (en) | Intelligent forklift identification obstacle avoidance method based on deepstream | |
| CN113011212B (en) | Image recognition method and device and vehicle | |
| CN113379669A (en) | Method, device and equipment for beverage cabinet image recognition | |
| JP2002008028A (en) | Pattern matching method and device therefor |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |