CN112115809A - Visitor matching method and device based on nearest neighbor algorithm - Google Patents
Visitor matching method and device based on nearest neighbor algorithm Download PDFInfo
- Publication number
- CN112115809A CN112115809A CN202010887013.0A CN202010887013A CN112115809A CN 112115809 A CN112115809 A CN 112115809A CN 202010887013 A CN202010887013 A CN 202010887013A CN 112115809 A CN112115809 A CN 112115809A
- Authority
- CN
- China
- Prior art keywords
- visitor
- face information
- information
- matching
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 34
- 238000012790 confirmation Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Abstract
The application discloses a visitor matching method and device based on a nearest neighbor algorithm, which are used for solving the problems of low identification accuracy and single function of the existing access control system. The method comprises the steps of collecting and detecting face information of a visitor; extracting the features of the face information; matching the face information with the face information of the visitor according to the face information prestored in the database, and classifying the face information based on a nearest neighbor algorithm; and prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result. The method can automatically identify the identity of the visitor, realize automatic door opening and provide convenience for users.
Description
Technical Field
The application relates to the field of face recognition, in particular to a visitor matching method and device based on a nearest neighbor algorithm.
Background
With the development of science and technology, various intelligent algorithms are more and more widely applied.
At present, in access control systems such as hotels and residential areas, a face recognition technology is often applied to automatically recognize the identities of visitors so as to realize intelligent control of the access control systems.
However, when the identity of a visitor is intelligently identified by the existing access control system, the problems of low identification accuracy, single function and the like still exist.
Disclosure of Invention
The embodiment of the application provides a visitor matching method and device based on a nearest neighbor algorithm, and aims to solve the problems of low identification accuracy and single function of the existing access control system.
The visitor matching method based on the nearest neighbor algorithm provided by the embodiment of the application comprises the following steps:
collecting and detecting face information of a visitor;
extracting the features of the face information;
matching the face information with the face information of the visitor according to the face information prestored in the database, and classifying the face information based on a nearest neighbor algorithm;
and prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result.
In one example, the face information of the visitor is collected and detected, and the method comprises the following steps: the face information of the visitor is collected through an OpenCV and multitask convolution neural network, and the position of the face information is detected.
In one example, the feature extraction of the face information includes: and extracting the face features in the face information through an instightface algorithm.
In one example, classifying the face information based on a nearest neighbor algorithm includes: collecting wearing information of a visitor; determining all wearing information prestored in a database and corresponding classifications; and determining the category to which the acquired wearing information belongs as the category to which the face information of the visitor belongs based on a nearest neighbor algorithm according to the acquired wearing information and the wearing information prestored in the database.
In one example, the step of prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result comprises the following steps: and prompting the identity corresponding to the visitor to the user according to the identity information corresponding to the face information matched with the face information in the database or according to a preset label corresponding to the category to which the face information belongs.
In one example, the method further comprises: and if the matching result is matching failure, prompting matching failure information to a user, collecting and inputting the identity information of the visitor, and correspondingly storing the identity information and the face information.
In one example, the method further comprises: and collecting a voice instruction of a user, performing voice recognition, and controlling a corresponding access control system according to a voice recognition result.
In one example, the method further comprises: if the access control system is monitored to be opened under the condition of failed matching, a safety confirmation request is sent to the user within a preset time period, and automatic alarm is given when the safety confirmation information of the user is not received.
In one example, the method further comprises: and prompting a user when determining that the visitor is a dangerous visitor according to dangerous visitor information prestored in a database.
The visitor matching device based on the nearest neighbor algorithm provided by the embodiment of the application comprises:
the acquisition module is used for acquiring and detecting the face information of the visitor;
the extraction module is used for extracting the characteristics of the face information;
the matching module is used for matching the face information of the visitor according to the face information prestored in the database and classifying the face information based on a nearest neighbor algorithm;
and the prompting module prompts the identity confirmation result of the visitor to the user according to the matching result and the classification result.
The embodiment of the application provides a visitor matching method and device based on a nearest neighbor algorithm, identity information of visitors can be automatically identified by detecting, identifying and matching face information of the visitors, and the identities of the visitors are classified so as to provide more information for users and facilitate the users to control the opening and closing of an access control system. Moreover, through the voice recognition technology, the instruction sent by the user is automatically recognized, the trouble that the user gets up to open the door can be avoided, automation and intellectualization are realized, and convenience is provided for the user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a visitor matching method based on a nearest neighbor algorithm according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a visitor matching device based on a nearest neighbor algorithm according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a flowchart of a visitor matching method based on a nearest neighbor algorithm according to an embodiment of the present application, which specifically includes the following steps:
s101: the face information of the visitor is collected and detected.
In the embodiment of the application, the access control system can acquire the face information of the visitor through an internal camera or an external camera, and detect the position coordinates of the face information in the acquired picture through a corresponding face detection algorithm.
In one embodiment, the access control system can acquire surrounding environment information in real time and detect a real-time monitored picture through a related algorithm function preset in an OpenCv framework. If the face information exists in the collected picture, further precision detection of the currently collected face information can be determined.
In one embodiment, the access control system may perform precision detection and positioning on the acquired face information through a Multi-task convolutional neural network (mtcnn).
Specifically, the process of the mtcnn model for face detection mainly comprises the following steps:
firstly, the mtcnn model can transform the size of the collected face information image to construct an image pyramid.
Secondly, the mtcnn model can judge whether part of the collected face information image is a face through a face classifier through a generation Network (P-Net) in a Network architecture, and simultaneously, a preliminary Proposal of the face region is provided by adopting frame regression and a face key point positioner so as to quickly generate a plurality of candidate windows of the face.
Thirdly, the mtcnn model can judge the prediction effect of the candidate windows of the faces determined in the second step through a filter Network (R-Net), filter out windows with poor effect and most likely errors, perform high-precision filtering and refining selection on the candidate windows, and output more credible face candidate windows.
Fourthly, the mtcnn model can perform face discrimination through an Output Network (O-Net) and perform regression on the face feature points to determine the final bounding box of the detected face information and the face key points.
Carry out face detection to the face information who gathers through mtcnn model, have higher detection precision and detection accuracy, can improve the accuracy that detects the face position that obtains to a certain extent to provide the basis for follow-up face identification.
S102: and extracting the characteristics of the face information.
In the embodiment of the application, the access control system can extract the characteristics of the detected face information so as to identify the identity of the visitor according to the extracted face characteristics.
In one embodiment, the access control system may specifically process the face information with the determined position through an insight face algorithm to extract the face features in the face information.
S103: and matching the face information with the face information of the visitor according to the face information prestored in the database, and classifying the face information based on a nearest neighbor algorithm.
In the embodiment of the application, the access control system can acquire the face feature information of some visitors in advance and correspondingly store the face feature information of each person and the identity information of each person. Thus, the database may include a large amount of facial feature information corresponding to several visitors.
When the access control system confirms the identity of the current visitor, the extracted face features of the visitor can be matched with all face features prestored in the database, and whether the face features matched with the face features of the visitor exist or not is determined.
If the face features matched with the face features of the visitor exist in the database, the fact that the identity information is input by the visitor through the access control system at present is shown. The access control system can confirm the identity information of the visitor according to the identity information stored in the database through the matching result. The identity information may include name, gender, age, occupation, etc.
If the database does not have the face features matched with the face features of the visiting persons, the fact that the identity information of the current visiting persons is not input into the access control system is shown, and the current visiting persons are probably strangers, face feature matching fails.
However, in places such as hotels and guest houses, the flow of people is often large, and the mobility of people is high, and particularly, visiting people such as takeout persons and couriers cannot usually enter identity information in advance. Therefore, in order to clarify the identity of the visitor, the access control system can classify the visitor according to the identity of the visitor according to a classification algorithm, so as to realize intelligent identification of the identity of the visitor.
In one embodiment, when the access control system collects the face information, the wearing information of the visitor can be collected together, and the wearing information and the face information are correspondingly stored. The wearing information of visitors with different identities often has corresponding obvious characteristics and can be subsequently used for comparing the characteristics and identifying the identities. The wearing information may include the clothing of the visitor, the helmet worn, and the like.
Specifically, the access control system can classify the stored identities of all visitors according to the wearing information stored in the database and the corresponding identity information in advance, determine the type of each wearing information, and set corresponding labels for each category. For example, in an access control system for a hotel, visitors may be divided into takeoffs, hotel workers, general users, and the like.
In the process of identifying the identity of the current visitor, if the access control system cannot determine the identity information matched with the face information of the visitor in the database, the wearing information and the face information of the current visitor can be classified according to a nearest neighbor (KNN) algorithm and the wearing information prestored in the database so as to determine the identity category corresponding to the visitor.
Specifically, the process of classifying the face information and the wearing information of the visitor mainly comprises the following steps:
firstly, according to the wearing information of the visitor, the distance between the wearing information and all the wearing information prestored in the database is calculated. All face information and wearing information used for calculation can be represented through vectors, the distance between the face information and the wearing information can be used for representing the similarity degree between face features and wearing features, the closer the distance is, the higher the similarity degree is, the farther the distance is, and the lower the similarity degree is.
Second, the distances are sorted according to all calculated distances. And determining K points which are closest to the wearing information of the current visitor according to a preset value K. Wherein, K can be set as required, which is not limited in the present application.
Thirdly, determining the categories to which the K points belong respectively.
Fourthly, determining the category with the largest number of categories into which the K points fall as the category into which the wearing information of the visitor falls. Wherein, the larger the number of categories into which the K points fall, that is, the larger the number of points similar to the current wearing information in the category, the higher the degree of similarity of the wearing information of the visitor to the category.
Therefore, the access control system can determine the category to which the wearing information of the visitor belongs, namely the category to which the face information belongs, by classification.
S104: and prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result.
In the embodiment of the application, the access control system can determine the identity information of the visitor according to the matching result of the face information of the visitor. And the access control system can also determine the identity category of the visitor according to the wearing information of the visitor. Therefore, the access control system can feed back the determined identity information or identity category as the identity confirmation result of the visitor to the user controlling the access control system.
In one embodiment, if the access control system can determine the face information in the database that matches the face information of the visitor, the specific identity information of the visitor can be directly determined. Therefore, the access control system can prompt the identity information of the visitor, including name, occupation and the like, to the user according to the prestored identity information.
If the access control system cannot determine the specific identity of the visitor, the access control system can prompt the user of matching failure information according to the preset label corresponding to the determined category to which the visitor belongs, and prompt the identity category of the visitor so that the user can judge whether to open the access control system.
In the embodiment of the application, the identity information of the visitor can be automatically identified by detecting, identifying and matching the face information of the visitor, and the identity of the visitor is classified so as to provide more information for the user and facilitate the user to control the opening and closing of the access control system. Moreover, through the voice recognition technology, the instruction sent by the user is automatically recognized, the trouble that the user gets up to open the door can be avoided, automation and intellectualization are realized, and convenience is provided for the user.
In one embodiment, if the access control system fails to match the face information of the visitor, indicating that the visitor has not entered information, the access control system may collect the identity information of the visitor and store the identity information in the database in correspondence with the face information of the visitor, so as to expand the data in the database.
In one embodiment, the access control system can monitor and collect the voice command of the user after prompting the identity confirmation result of the visitor to the user, perform voice recognition on the collected voice command, and determine the command content sent by the user. And then, the access control system can determine whether to open according to the voice recognition result, and allows visitors to pass through.
In one embodiment, if the face information of the visitor fails to be matched, it indicates that the visitor is a stranger, and a certain security risk exists. Therefore, if the access control system is monitored to be opened by the user under the condition that the face information of the visitor is not matched successfully, in order to ensure the safety of the user, the access control system can send a safety confirmation request to the user within a preset time period, and the user performs safety confirmation. The preset time period can be set according to needs, and the preset time period is not limited in the application.
If the access control system does not receive the safety confirmation information of the user within the preset time period, the user can be considered to have certain safety risk. Therefore, the access control system can automatically give an alarm, and store and mark the collected face information of the nearest visitor. Therefore, the personal safety of the user can be ensured to a certain extent, illegal persons are prevented from being disguised as takeout persons, couriers and the like, the user is deceived, and the personal safety of the user is threatened.
In one embodiment, the access control system can be in butt joint with a corresponding security system, and obtains illegal personnel information with illegal behaviors such as theft, robbery, fighting and the like stored in the security system, and the illegal personnel information is used as dangerous visitor information in a database of the access control system and stored. Therefore, the access control system can prompt the user when determining that the current visitor is a dangerous visitor through face recognition according to the information of the dangerous visitor stored in the database.
In one embodiment, if the access control system monitors that the visitor is a dangerous visitor and the user is not in the house, in order to prevent the dangerous visitor from attempting to steal or other illegal activities, the access control system may automatically play a corresponding voice segment according to a preset instruction of the user to create an illusion that someone is in the house.
Based on the same inventive idea, the visitor matching method based on the nearest neighbor algorithm provided in the embodiment of the present application further provides a corresponding visitor matching device based on the nearest neighbor algorithm, as shown in fig. 2.
Fig. 2 is a schematic structural diagram of a visitor matching device based on a nearest neighbor algorithm according to an embodiment of the present application, which specifically includes:
the acquisition module 201 is used for acquiring and detecting the face information of the visitor;
an extraction module 202, which extracts the features of the face information;
the matching module 203 is used for matching the face information of the visitor according to the face information prestored in the database and classifying the face information based on a nearest neighbor algorithm;
and the prompting module 204 is used for prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A visitor matching method based on a nearest neighbor algorithm is characterized by comprising the following steps:
collecting and detecting face information of a visitor;
extracting the features of the face information;
matching the face information with the face information of the visitor according to the face information prestored in the database, and classifying the face information based on a nearest neighbor algorithm;
and prompting the identity confirmation result of the visitor to the user according to the matching result and the classification result.
2. The method of claim 1, wherein collecting and detecting face information of a visitor comprises:
the face information of the visitor is collected through an OpenCV and multitask convolution neural network, and the position of the face information is detected.
3. The method of claim 1, wherein feature extracting the face information comprises:
and extracting the face features in the face information through an instightface algorithm.
4. The method of claim 1, wherein classifying the face information based on a nearest neighbor algorithm comprises:
collecting wearing information of a visitor;
determining all wearing information prestored in a database and corresponding classifications;
and determining the category to which the acquired wearing information belongs as the category to which the face information of the visitor belongs based on a nearest neighbor algorithm according to the acquired wearing information and the wearing information prestored in the database.
5. The method of claim 4, wherein prompting the user for the identity confirmation result of the visitor according to the matching result and the classification result comprises:
and prompting the identity corresponding to the visitor to the user according to the identity information corresponding to the face information matched with the face information in the database or according to a preset label corresponding to the category to which the face information belongs.
6. The method of claim 1, further comprising:
and if the matching result is matching failure, prompting matching failure information to a user, collecting and inputting the identity information of the visitor, and correspondingly storing the identity information and the face information.
7. The method of claim 1, further comprising:
and collecting a voice instruction of a user, performing voice recognition, and controlling a corresponding access control system according to a voice recognition result.
8. The method of claim 1, further comprising:
if the access control system is monitored to be opened under the condition of failed matching, a safety confirmation request is sent to the user within a preset time period, and automatic alarm is given when the safety confirmation information of the user is not received.
9. The method of claim 1, further comprising:
and prompting a user when determining that the visitor is a dangerous visitor according to dangerous visitor information prestored in a database.
10. A visitor matching device based on a nearest neighbor algorithm is characterized by comprising:
the acquisition module is used for acquiring and detecting the face information of the visitor;
the extraction module is used for extracting the characteristics of the face information;
the matching module is used for matching the face information of the visitor according to the face information prestored in the database and classifying the face information based on a nearest neighbor algorithm;
and the prompting module prompts the identity confirmation result of the visitor to the user according to the matching result and the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887013.0A CN112115809A (en) | 2020-08-28 | 2020-08-28 | Visitor matching method and device based on nearest neighbor algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887013.0A CN112115809A (en) | 2020-08-28 | 2020-08-28 | Visitor matching method and device based on nearest neighbor algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112115809A true CN112115809A (en) | 2020-12-22 |
Family
ID=73805031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010887013.0A Pending CN112115809A (en) | 2020-08-28 | 2020-08-28 | Visitor matching method and device based on nearest neighbor algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115809A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491830A (en) * | 2018-04-23 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning |
| CN108734146A (en) * | 2018-05-28 | 2018-11-02 | 北京达佳互联信息技术有限公司 | Facial image Age estimation method, apparatus, computer equipment and storage medium |
| CN108810471A (en) * | 2018-06-14 | 2018-11-13 | 北京奇虎科技有限公司 | A kind of intelligent doorbell, information sharing method and device |
| CN109598831A (en) * | 2018-11-20 | 2019-04-09 | 北京千丁互联科技有限公司 | A kind of visitor's access control system control method and its device based on image recognition |
| CN109830015A (en) * | 2019-01-29 | 2019-05-31 | 上海乐愚智能科技有限公司 | Visiting personnel recognition methods, device, intelligent peephole, server and storage medium |
| CN110363063A (en) * | 2019-05-17 | 2019-10-22 | 深圳市趣创科技有限公司 | Face identification method and system and its storage medium based on Fisherface and Nearest Neighbor Classifier |
| CN110598735A (en) * | 2019-08-05 | 2019-12-20 | 深圳市大拿科技有限公司 | Visitor information reminding method and device |
| CN111145417A (en) * | 2020-01-15 | 2020-05-12 | 快住智能科技（苏州）有限公司 | Access control system based on face recognition |
-
2020
- 2020-08-28 CN CN202010887013.0A patent/CN112115809A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491830A (en) * | 2018-04-23 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning |
| CN108734146A (en) * | 2018-05-28 | 2018-11-02 | 北京达佳互联信息技术有限公司 | Facial image Age estimation method, apparatus, computer equipment and storage medium |
| CN108810471A (en) * | 2018-06-14 | 2018-11-13 | 北京奇虎科技有限公司 | A kind of intelligent doorbell, information sharing method and device |
| CN109598831A (en) * | 2018-11-20 | 2019-04-09 | 北京千丁互联科技有限公司 | A kind of visitor's access control system control method and its device based on image recognition |
| CN109830015A (en) * | 2019-01-29 | 2019-05-31 | 上海乐愚智能科技有限公司 | Visiting personnel recognition methods, device, intelligent peephole, server and storage medium |
| CN110363063A (en) * | 2019-05-17 | 2019-10-22 | 深圳市趣创科技有限公司 | Face identification method and system and its storage medium based on Fisherface and Nearest Neighbor Classifier |
| CN110598735A (en) * | 2019-08-05 | 2019-12-20 | 深圳市大拿科技有限公司 | Visitor information reminding method and device |
| CN111145417A (en) * | 2020-01-15 | 2020-05-12 | 快住智能科技（苏州）有限公司 | Access control system based on face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110491004B (en) | Resident community personnel safety management system and method | |
| CN102201061B (en) | Intelligent safety monitoring system and method based on multilevel filtering face recognition | |
| CA2804468C (en) | System and method for face capture and matching | |
| CN109980781A (en) | A kind of transformer substation intelligent monitoring system | |
| CN105427421A (en) | Entrance guard control method based on face recognition | |
| WO2018180588A1 (en) | Facial image matching system and facial image search system | |
| US9477876B2 (en) | Person recognition apparatus and method thereof | |
| US8266174B2 (en) | Behavior history retrieval apparatus and behavior history retrieval method | |
| US20020176610A1 (en) | Face image recording system | |
| Li et al. | Face recognition applications | |
| CN109145801B (en) | Face recognition method and face recognition system | |
| WO2020195376A1 (en) | Monitoring device, suspicious object detecting method, and recording medium | |
| KR101957677B1 (en) | System for learning based real time guidance through face recognition and the method thereof | |
| CN112183162A (en) | Face automatic registration and recognition system and method in monitoring scene | |
| CN109784231A (en) | Safeguard information management method, device and storage medium | |
| CN116563797B (en) | Monitoring management system for intelligent campus | |
| EA038293B1 (en) | Method and system for detecting troubling events during interaction with a self-service device | |
| CN108537920B (en) | Visitor monitoring method and system based on face recognition | |
| CN111862413A (en) | Method and system for realizing epidemic situation resistant non-contact multidimensional identity rapid identification | |
| CN103443772A (en) | System and method for demographic analytics based on multimodal information | |
| US20220292170A1 (en) | Enrollment System with Continuous Learning and Confirmation | |
| CN110246292A (en) | Domestic video monitoring method, apparatus and storage medium | |
| CN111960200B (en) | Resident building elevator control system based on voice recognition and face recognition | |
| CN112330742A (en) | Method and device for recording activity routes of key personnel in public area | |
| CN112115809A (en) | Visitor matching method and device based on nearest neighbor algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201222 |