CN112070013A - Method and device for detecting facial feature points of children and storage medium - Google Patents
Method and device for detecting facial feature points of children and storage medium Download PDFInfo
- Publication number
- CN112070013A CN112070013A CN202010935353.6A CN202010935353A CN112070013A CN 112070013 A CN112070013 A CN 112070013A CN 202010935353 A CN202010935353 A CN 202010935353A CN 112070013 A CN112070013 A CN 112070013A
- Authority
- CN
- China
- Prior art keywords
- point
- coordinate
- verification
- line segment
- difference
- 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
Images
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
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Abstract
The invention discloses a method, a device and a storage medium for detecting facial feature points of children, which comprises the following steps: the method comprises the following steps: acquiring the image information of the face of the child through an image acquisition terminal of a detection device; step two: extracting feature points of the acquired real-time child face image; step three: establishing a real-time identification and verification coordinate system, and marking the real-time child face image characteristic points on the real-time verification coordinate system; step four: extracting a pre-stored verification coordinate point in a database and comparing the pre-stored verification coordinate point with a verification coordinate system; step five: after the coordinate verification is passed, connecting the coordinate points to obtain a verification model, and when the verification model passes, passing the child identity verification; step six: after the verification is passed, replacing the pre-stored characteristic points with the collected children face characteristic points, and storing the characteristic points in the database as the pre-stored characteristic points for the next verification. The invention can more accurately and more quickly detect the human face characteristic points.
Description
Technical Field
The invention relates to the field of face verification, in particular to a method and a device for detecting facial feature points of children and a storage medium.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. The method is characterized in that a camera or a camera is used for collecting images or video streams containing human faces, the human faces are automatically detected and tracked in the images, and then a series of related technologies for carrying out face identification on the detected human faces are commonly called portrait identification and face identification, the human faces are unique like other biological characteristics (fingerprints, irises and the like) of human bodies, the uniqueness and the good characteristic that the human faces are not easily copied provide necessary premise for identity identification, and when the human faces are identified, characteristic points of the human faces need to be extracted for carrying out the characteristic identification.
The existing human feature point detection method is easy to generate larger deviation when detecting feature points, so that the error probability of final verification is increased, and certain influence is brought to the use of the human feature point detection method.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to solve the problem that when the existing method for detecting the human characteristic points detects the characteristic points, larger deviation is easy to occur, the error probability of final verification is increased, and the problem that the use of the method for detecting the human characteristic points is influenced to a certain extent is solved.
The invention solves the technical problems through the following technical scheme, and the invention comprises the following steps:
the method comprises the following steps: acquiring the image information of the face of the child through an image acquisition terminal of a detection device;
step two: extracting feature points of the acquired real-time child face image;
step three: establishing a real-time identification and verification coordinate system, and marking the real-time child face image characteristic points on the real-time verification coordinate system;
step four: extracting a pre-stored verification coordinate point in a database and comparing the pre-stored verification coordinate point with a verification coordinate system;
step five: after the coordinate verification is passed, connecting the coordinate points to obtain a verification model, and when the verification model passes, passing the child identity verification;
step six: after the verification is passed, replacing the pre-stored characteristic points with the collected children face characteristic points, and storing the characteristic points in the database as the pre-stored characteristic points for the next verification.
Preferably, the child face image acquired in the first step is a child face image photo.
Preferably, the feature point extraction process in the second step is as follows
The method comprises the following steps: extracting the image information of the face of the child;
step two: marking two outer eye corner points of the face in the child face image information as a point A1 and a point A2 respectively;
step three: marking the points of two mouth corners in the face image information as a point A3 and a point A4 respectively;
step four: marking the nose tip point of the face in the face image center as a point A4;
step five: establishing a plane rectangular coordinate system K by taking the point A4 as an origin, and acquiring a coordinate A1(x1, y1) of the point A1, a coordinate A2(x2, y2) of the point A2, a coordinate A3(x3, y3) of the point A3 and a coordinate A4(x4, y4) of the point A4;
step six: extracting and comparing coordinates A1(x1, y1) of the point A1, coordinates A2(x2, y2) of the point A2, coordinates A3(x3, y3) of the point A3 and coordinates A4(x4, y4) of the point A4 with coordinate coefficients of pre-stored characteristic points pre-stored in a database;
step seven: when the coordinate difference between the coordinate a1(x1, y1) of the calculated point a1 and the coordinate difference between the prestored a1 point, when the coordinate difference is smaller than the preset value, the point a1 is verified to pass, when the coordinate difference between the coordinate a2(x2, y2) of the calculated point a2 and the coordinate difference between the prestored a2 point is smaller than the preset value, the point a2 is verified to pass, when the coordinate difference between the coordinate A3(x3, y3) of the calculated point A3 and the coordinate difference between the prestored A3 point is smaller than the preset value, the point A3 is verified to pass, when the coordinate difference between the coordinate a4(x4, y4) of the calculated point a4 and the coordinate difference between the prestored a4 point is smaller than the preset value, the point a4 is verified to pass;
step eight: when the point A1, the point A2, the point A3 and the point A4 are verified to pass, the verification passes in real time, and then verification model comparison is carried out on the verification passing;
step nine: connecting a point A1 with a point A2 to obtain a line segment L1, connecting a point A2 with a point A4 to obtain a line segment L2, connecting a point A4 with a point A3 to obtain a line segment L3, and connecting a point A3 with a point A1 to obtain a line segment L4;
step ten: the line segment L1, the line segment L2, the line segment L3 and the line segment L4 enclose a trapezoid M;
step eleven: making a vertical line segment L5 between a line segment L1 and a line segment L3, and measuring the lengths of the line segment L1, the line segment L3 and a vertical line segment L5;
step twelve: by the formula (L1+ L3) L5/2 ═ SLadder with adjustable heightObtaining the real-time verification model area SLadder with adjustable height；
Step thirteen: extracting the area S of the pre-stored modelPreparation ofAnd calculating the area S of the pre-stored modelPreparation ofAnd real-time verification of model area SLadder with adjustable heightDifference between them, obtaining area difference SDifference (D)When area difference SDifference (D)The absolute value of (a) is within a preset range.
A detection device used in a detection method of facial feature points of children comprises a device main body, wherein a light supplement lamp is arranged at a position, close to a corner, outside the front end of the device main body, a camera is arranged at the middle position outside the front end of the device main body, a support rod is arranged at the top end of the device main body, a viewing frame is fixedly installed at the front end of the support rod, and a head support fixedly installed through an elastic column is arranged inside the viewing frame;
the bracing piece includes the first body of rod and the second body of rod, the spread groove has been seted up to the inside of the second body of rod, the inside of spread groove be provided with the connecting block of first body of rod fixed connection.
A storage medium used in a method for detecting facial feature points of children comprises a computer data storage hard disk and a network cloud disk.
Compared with the prior art, the invention has the following advantages: this detection method of children's people's face characteristic point, device and storage medium, can better gather children's face image information, the effectual identification that has reduced the unclear discernment that leads to of children's face image is verified and is failed, and the setting of dual verification, can better verify, the effectual unexpected emergence of leading to of having avoided verifying to make mistakes, effectual improvement verify improve accuracy and the real-time that children's people's face characteristic point detected effectively, and the running rate, and through the data that will verify at every turn and carry out replacement processing's setting, can also can accomplish the discernment when the small change takes place at children's image, make this kind of detection method be worth using widely more.
Drawings
FIG. 1 is a block flow diagram of the present invention;
FIG. 2 is an overall configuration diagram of the inspection apparatus of the present invention;
fig. 3 is an overall structure diagram of a support bar of the measuring device of the present invention.
In the figure: 1. a device main body; 2. a light supplement lamp; 3. a camera; 4. a support bar; 41. a first rod body; 42. a second rod body; 43. connecting grooves; 44. connecting blocks; 5. a viewing frame; 6. an elastic column; 7. a head support.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
As shown in fig. 1, the present embodiment provides a technical solution: a method for detecting facial feature points of children comprises the following steps:
the method comprises the following steps: acquiring the image information of the face of the child through an image acquisition terminal of a detection device;
step two: extracting feature points of the acquired real-time child face image;
step three: establishing a real-time identification and verification coordinate system, and marking the real-time child face image characteristic points on the real-time verification coordinate system;
step four: extracting a pre-stored verification coordinate point in a database and comparing the pre-stored verification coordinate point with a verification coordinate system;
step five: after the coordinate verification is passed, connecting the coordinate points to obtain a verification model, and when the verification model passes, passing the child identity verification;
step six: after the verification is passed, replacing the pre-stored characteristic points with the collected children face characteristic points, and storing the characteristic points in the database as the pre-stored characteristic points for the next verification.
The child face image acquired in the first step is a child face image photo.
The characteristic point extraction process in the second step is as follows
The method comprises the following steps: extracting the image information of the face of the child;
step two: marking two outer eye corner points of the face in the child face image information as a point A1 and a point A2 respectively;
step three: marking the points of two mouth corners in the face image information as a point A3 and a point A4 respectively;
step four: marking the nose tip point of the face in the face image center as a point A4;
step five: establishing a plane rectangular coordinate system K by taking the point A4 as an origin, and acquiring a coordinate A1(x1, y1) of the point A1, a coordinate A2(x2, y2) of the point A2, a coordinate A3(x3, y3) of the point A3 and a coordinate A4(x4, y4) of the point A4;
step six: extracting and comparing coordinates A1(x1, y1) of the point A1, coordinates A2(x2, y2) of the point A2, coordinates A3(x3, y3) of the point A3 and coordinates A4(x4, y4) of the point A4 with coordinate coefficients of pre-stored characteristic points pre-stored in a database;
step seven: when the coordinate difference between the coordinate a1(x1, y1) of the calculated point a1 and the coordinate difference between the prestored a1 point, when the coordinate difference is smaller than the preset value, the point a1 is verified to pass, when the coordinate difference between the coordinate a2(x2, y2) of the calculated point a2 and the coordinate difference between the prestored a2 point is smaller than the preset value, the point a2 is verified to pass, when the coordinate difference between the coordinate A3(x3, y3) of the calculated point A3 and the coordinate difference between the prestored A3 point is smaller than the preset value, the point A3 is verified to pass, when the coordinate difference between the coordinate a4(x4, y4) of the calculated point a4 and the coordinate difference between the prestored a4 point is smaller than the preset value, the point a4 is verified to pass;
step eight: when the point A1, the point A2, the point A3 and the point A4 are verified to pass, the verification passes in real time, and then verification model comparison is carried out on the verification passing;
step nine: connecting a point A1 with a point A2 to obtain a line segment L1, connecting a point A2 with a point A4 to obtain a line segment L2, connecting a point A4 with a point A3 to obtain a line segment L3, and connecting a point A3 with a point A1 to obtain a line segment L4;
step ten: the line segment L1, the line segment L2, the line segment L3 and the line segment L4 enclose a trapezoid M;
step eleven: making a vertical line segment L5 between a line segment L1 and a line segment L3, and measuring the lengths of the line segment L1, the line segment L3 and a vertical line segment L5;
step twelve: by the formula (L1+ L3) L5/2 ═ SLadder with adjustable heightObtaining the real-time verification model area SLadder with adjustable height；
Step thirteen: extracting the area S of the pre-stored modelPreparation ofAnd calculating the area S of the pre-stored modelPreparation ofAnd real-time verification of model area SLadder with adjustable heightDifference between them, obtaining area difference SDifference (D)When area difference SDifference (D)The absolute value of (a) is within a preset range.
As shown in fig. 2 and 3, a detection device used in a method for detecting facial feature points of children comprises a device main body 1, a light supplement lamp 2 is arranged at a position, close to a corner, outside the front end of the device main body 1, a camera 3 is arranged at a middle position outside the front end of the device main body 1, a support rod 4 is arranged at the top end of the device main body 1, a view finder 5 is fixedly installed at the front end of the support rod 4, and a head support 7 fixedly installed through an elastic column 6 is arranged inside the view finder 5;
the supporting rod 4 comprises a first rod body 41 and a second rod body 42, a connecting groove 43 is formed in the second rod body 42, and a connecting block 44 fixedly connected with the first rod body 41 is arranged in the connecting groove 43;
children stretch into the head in the frame of finding a view 5, place the head on head support 7, 6 outrigger head supports 7 of elasticity post to can come the pulling bracing piece 4 to change the length of bracing piece 4 according to the demand, later open the light filling lamp 2 that corresponds quantity according to the in-service use demand, camera 3 begins promptly to obtain children's people face image after light is beaten to light filling lamp 2.
A storage medium used in a method for detecting facial feature points of children comprises a computer data storage hard disk and a network cloud disk.
In summary, when the invention is used, a child inserts the head into the viewfinder frame 5, places the head on the head support 7, the elastic column 6 stably supports the head support 7, and can pull the support rod 4 to change the length of the support rod 4 according to the requirement, then turns on the corresponding number of the light supplement lamps 2 according to the requirement of actual use, the camera 3 starts to acquire the child face image after the light supplement lamps 2 are lighted, the acquired real-time child face image is subjected to feature point extraction, a real-time identification verification coordinate system is established, then the real-time child face image feature points are marked on the real-time verification coordinate system, the pre-stored verification coordinate points in the database are extracted and compared with the verification coordinate system, after the coordinate verification is passed, the coordinate points are connected to obtain a verification model, when the verification model is passed, namely the child identity verification is passed, after the verification is passed, and replacing the pre-stored characteristic points with the collected facial characteristic points of the children, and storing the facial characteristic points of the children in the database as the pre-stored characteristic points for next verification.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (5)
1. A method for detecting facial feature points of children is characterized by comprising the following steps:
the method comprises the following steps: acquiring the image information of the face of the child through an image acquisition terminal of a detection device;
step two: extracting feature points of the acquired real-time child face image;
step three: establishing a real-time identification and verification coordinate system, and marking the real-time child face image characteristic points on the real-time verification coordinate system;
step four: extracting a pre-stored verification coordinate point in a database and comparing the pre-stored verification coordinate point with a verification coordinate system;
step five: after the coordinate verification is passed, connecting the coordinate points to obtain a verification model, and when the verification model passes, passing the child identity verification;
step six: after the verification is passed, replacing the pre-stored characteristic points with the collected children face characteristic points, and storing the characteristic points in the database as the pre-stored characteristic points for the next verification.
2. The method for detecting facial feature points of children as claimed in claim 1, wherein: the child face image acquired in the first step is a child face image photo.
3. The method for detecting facial feature points of children as claimed in claim 1, wherein: the characteristic point extraction process in the second step is as follows
The method comprises the following steps: extracting the image information of the face of the child;
step two: marking two outer eye corner points of the face in the child face image information as a point A1 and a point A2 respectively;
step three: marking the points of two mouth corners in the face image information as a point A3 and a point A4 respectively;
step four: marking the nose tip point of the face in the face image center as a point A4;
step five: establishing a plane rectangular coordinate system K by taking the point A4 as an origin, and acquiring a coordinate A1(x1, y1) of the point A1, a coordinate A2(x2, y2) of the point A2, a coordinate A3(x3, y3) of the point A3 and a coordinate A4(x4, y4) of the point A4;
step six: extracting and comparing coordinates A1(x1, y1) of the point A1, coordinates A2(x2, y2) of the point A2, coordinates A3(x3, y3) of the point A3 and coordinates A4(x4, y4) of the point A4 with coordinate coefficients of pre-stored characteristic points pre-stored in a database;
step seven: when the coordinate difference between the coordinate a1(x1, y1) of the calculated point a1 and the coordinate difference between the prestored a1 point, when the coordinate difference is smaller than the preset value, the point a1 is verified to pass, when the coordinate difference between the coordinate a2(x2, y2) of the calculated point a2 and the coordinate difference between the prestored a2 point is smaller than the preset value, the point a2 is verified to pass, when the coordinate difference between the coordinate A3(x3, y3) of the calculated point A3 and the coordinate difference between the prestored A3 point is smaller than the preset value, the point A3 is verified to pass, when the coordinate difference between the coordinate a4(x4, y4) of the calculated point a4 and the coordinate difference between the prestored a4 point is smaller than the preset value, the point a4 is verified to pass;
step eight: when the point A1, the point A2, the point A3 and the point A4 are verified to pass, the verification passes in real time, and then verification model comparison is carried out on the verification passing;
step nine: connecting a point A1 with a point A2 to obtain a line segment L1, connecting a point A2 with a point A4 to obtain a line segment L2, connecting a point A4 with a point A3 to obtain a line segment L3, and connecting a point A3 with a point A1 to obtain a line segment L4;
step ten: the line segment L1, the line segment L2, the line segment L3 and the line segment L4 enclose a trapezoid M;
step eleven: making a vertical line segment L5 between a line segment L1 and a line segment L3, and measuring the lengths of the line segment L1, the line segment L3 and a vertical line segment L5;
step twelve: by the formula (L1+ L3) L5/2 ═ SLadder with adjustable heightObtaining the real-time verification model area SLadder with adjustable height；
Step thirteen: extracting to obtain pre-extractArea of model storage SPreparation ofAnd calculating the area S of the pre-stored modelPreparation ofAnd real-time verification of model area SLadder with adjustable heightDifference between them, obtaining area difference SDifference (D)When area difference SDifference (D)The absolute value of (a) is within a preset range.
4. The method for detecting facial feature points of children as claimed in claim 1, wherein: the detection device used by the detection method of the facial feature points of the children comprises a device main body (1), a light supplement lamp (2) is arranged at a position, close to corners, outside the front end of the device main body (1), a camera (3) is arranged at a middle position outside the front end of the device main body (1), a support rod (4) is arranged at the top end of the device main body (1), a view finding frame (5) is fixedly installed at the front end of the support rod (4), and a head support (7) fixedly installed through an elastic column (6) is arranged inside the view finding frame (5);
the bracing piece (4) include the first body of rod (41) and the second body of rod (42), spread groove (43) have been seted up to the inside of the second body of rod (42), the inside of spread groove (43) is provided with connecting block (44) with the first body of rod (41) fixed connection.
5. The method for detecting facial feature points of children as claimed in claim 1, wherein: the storage medium used by the method for detecting the facial feature points of the children comprises a computer data storage hard disk and a network cloud disk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935353.6A CN112070013A (en) | 2020-09-08 | 2020-09-08 | Method and device for detecting facial feature points of children and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935353.6A CN112070013A (en) | 2020-09-08 | 2020-09-08 | Method and device for detecting facial feature points of children and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070013A true CN112070013A (en) | 2020-12-11 |
Family
ID=73664377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010935353.6A Pending CN112070013A (en) | 2020-09-08 | 2020-09-08 | Method and device for detecting facial feature points of children and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070013A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030198368A1 (en) * | 2002-04-23 | 2003-10-23 | Samsung Electronics Co., Ltd. | Method for verifying users and updating database, and face verification system using the same |
| CN102194131A (en) * | 2011-06-01 | 2011-09-21 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| CN103914676A (en) * | 2012-12-30 | 2014-07-09 | 杭州朗和科技有限公司 | Method and apparatus for use in face recognition |
| CN207424942U (en) * | 2017-11-29 | 2018-05-29 | 广州鸿海软件科技有限公司 | A kind of face ticket automatic recognition system |
| CN108537143A (en) * | 2018-03-21 | 2018-09-14 | 特斯联（北京）科技有限公司 | A kind of face identification method and system based on key area aspect ratio pair |
| CN108875549A (en) * | 2018-04-20 | 2018-11-23 | 北京旷视科技有限公司 | Image-recognizing method, device, system and computer storage medium |
| CN109409060A (en) * | 2018-09-26 | 2019-03-01 | 中国平安人寿保险股份有限公司 | Auth method, system and computer readable storage medium |
| CN109544721A (en) * | 2018-12-04 | 2019-03-29 | 北京诺士诚国际工程项目管理有限公司 | A kind of long-range punch card method and system |
| CN109902463A (en) * | 2019-04-02 | 2019-06-18 | 广州任天游网络科技有限公司 | A kind of immigrant's consultation service platform login system based on recognition of face |
| CN110096988A (en) * | 2019-04-24 | 2019-08-06 | 上海益创信息科技有限公司 | A kind of self-service personnel identity verifying system based on recognition of face |
| CN110705357A (en) * | 2019-09-02 | 2020-01-17 | 深圳中兴网信科技有限公司 | Face recognition method and face recognition device |
| CN111091031A (en) * | 2018-10-24 | 2020-05-01 | 北京旷视科技有限公司 | Target object selection method and face unlocking method |
| CN111582118A (en) * | 2020-04-29 | 2020-08-25 | 福州瑞芯微电子股份有限公司 | Face recognition method and device |
| US20200320322A1 (en) * | 2018-04-04 | 2020-10-08 | Beijing Sensetime Technology Development Co., Ltd. | Methods and apparatuses for processing image and identity verification, electronic devices, and storage media |
-
2020
- 2020-09-08 CN CN202010935353.6A patent/CN112070013A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030198368A1 (en) * | 2002-04-23 | 2003-10-23 | Samsung Electronics Co., Ltd. | Method for verifying users and updating database, and face verification system using the same |
| CN102194131A (en) * | 2011-06-01 | 2011-09-21 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| CN103914676A (en) * | 2012-12-30 | 2014-07-09 | 杭州朗和科技有限公司 | Method and apparatus for use in face recognition |
| CN207424942U (en) * | 2017-11-29 | 2018-05-29 | 广州鸿海软件科技有限公司 | A kind of face ticket automatic recognition system |
| CN108537143A (en) * | 2018-03-21 | 2018-09-14 | 特斯联（北京）科技有限公司 | A kind of face identification method and system based on key area aspect ratio pair |
| US20200320322A1 (en) * | 2018-04-04 | 2020-10-08 | Beijing Sensetime Technology Development Co., Ltd. | Methods and apparatuses for processing image and identity verification, electronic devices, and storage media |
| CN108875549A (en) * | 2018-04-20 | 2018-11-23 | 北京旷视科技有限公司 | Image-recognizing method, device, system and computer storage medium |
| CN109409060A (en) * | 2018-09-26 | 2019-03-01 | 中国平安人寿保险股份有限公司 | Auth method, system and computer readable storage medium |
| CN111091031A (en) * | 2018-10-24 | 2020-05-01 | 北京旷视科技有限公司 | Target object selection method and face unlocking method |
| CN109544721A (en) * | 2018-12-04 | 2019-03-29 | 北京诺士诚国际工程项目管理有限公司 | A kind of long-range punch card method and system |
| CN109902463A (en) * | 2019-04-02 | 2019-06-18 | 广州任天游网络科技有限公司 | A kind of immigrant's consultation service platform login system based on recognition of face |
| CN110096988A (en) * | 2019-04-24 | 2019-08-06 | 上海益创信息科技有限公司 | A kind of self-service personnel identity verifying system based on recognition of face |
| CN110705357A (en) * | 2019-09-02 | 2020-01-17 | 深圳中兴网信科技有限公司 | Face recognition method and face recognition device |
| CN111582118A (en) * | 2020-04-29 | 2020-08-25 | 福州瑞芯微电子股份有限公司 | Face recognition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021036436A1 (en) | Facial recognition method and apparatus | |
| WO2020134527A1 (en) | Method and apparatus for face recognition | |
| CN105740778B (en) | Improved three-dimensional human face in-vivo detection method and device | |
| CN105654048A (en) | Multi-visual-angle face comparison method | |
| CN106250825A (en) | A kind of at the medical insurance adaptive face identification system of applications fields scape | |
| KR101821144B1 (en) | Access Control System using Depth Information based Face Recognition | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN110309701A (en) | It is a kind of based on the pedestrian across visual angle the same area again recognition methods | |
| WO2019127319A1 (en) | Distortion measurement method and system for head-mounted display device | |
| CN114894337B (en) | Temperature measurement method and device for outdoor face recognition | |
| CN107944395A (en) | A kind of method and system based on neutral net verification testimony of a witness unification | |
| CN111814702A (en) | Child face recognition method based on adult face and child photo feature space mapping relation | |
| CN109087429B (en) | Method for checking consistency of library book-borrowing testimony of witness based on face recognition technology | |
| US20120076368A1 (en) | Face identification based on facial feature changes | |
| CN109389085B (en) | Lip language recognition model training method and device based on parameterized curve | |
| CN114332942A (en) | Night infrared pedestrian detection method and system based on improved YOLOv3 | |
| CN111814701A (en) | Children face recognition algorithm for feature migration learning based on double-layer heterogeneous network | |
| CN112070013A (en) | Method and device for detecting facial feature points of children and storage medium | |
| CN110909617B (en) | Living body face detection method and device based on binocular vision | |
| CN116453198B (en) | Sight line calibration method and device based on head posture difference | |
| CN107705357A (en) | Lie detecting method and device | |
| CN112257507A (en) | Method and device for judging distance and human face validity based on human face interpupillary distance | |
| CN110363818A (en) | The method for detecting abnormality and device of binocular vision system | |
| CN112802051B (en) | Fitting method and system of basketball shooting curve based on neural network | |
| CN115410261A (en) | Face recognition heterogeneous data association analysis system |
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 |