CN214151721U - Recognition all-in-one machine system based on face algorithm - Google Patents
Recognition all-in-one machine system based on face algorithm Download PDFInfo
- Publication number
- CN214151721U CN214151721U CN202022816990.XU CN202022816990U CN214151721U CN 214151721 U CN214151721 U CN 214151721U CN 202022816990 U CN202022816990 U CN 202022816990U CN 214151721 U CN214151721 U CN 214151721U
- Authority
- CN
- China
- Prior art keywords
- face
- module
- recognition
- camera
- algorithm
- 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
Images
Abstract
The utility model discloses a discernment all-in-one system based on face algorithm, its characterized in that: the system comprises a camera, wherein the camera is in wireless connection with a mobile phone client and a CMS client remote control system; the camera comprises an image shooting module, a face positioning module, an image preprocessing module, a face recognition module and a storage module, wherein the face positioning module, the image preprocessing module, the face recognition module and the storage module are connected with the image shooting module; the face positioning module comprises a face inspection module and a face registration module. The utility model discloses adapt to face identification under the various environmental condition, dynamic video intellectual detection system analysis people's face, according to highlight/night vision/low light level, sun backlight/hall backlight/low light backlight environment, intelligent people's face exposes, guarantees to obtain the optimal people's face picture. Meanwhile, a deep learning intelligent face algorithm is embedded, and automatic detection, automatic tracking and automatic snapshot are carried out on the moving face; grading, screening, removing weight, and preferentially outputting a face picture most suitable for face recognition.
Description
Technical Field
The utility model relates to a discernment all-in-one system, in particular to discernment all-in-one system based on face algorithm.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. The method comprises the steps of collecting images or video streams containing human faces by using a camera or a pick-up head, firstly judging whether the human faces exist, and further giving the position and the size of each face and the position information of each main facial organ if the human faces exist. And further extracting the identity characteristics implied in each face according to the information, and comparing the identity characteristics with the known faces so as to identify the identity of each face.
The existing face recognition camera architecture adopts a single processor architecture, namely, business and algorithm are realized, a camera is only responsible for snapshot, and the recognition function is operated at the cloud. The single processor solution requires a high performance of the processor and is relatively costly. The camera is only responsible for collecting face pictures, the pictures need to be uploaded to the cloud for processing and analysis through the recognition function, more network bandwidth needs to be occupied, the computing pressure of the cloud is increased, and the real-time performance and the data privacy are reduced.
Disclosure of Invention
The utility model discloses a remedy prior art not enough, provide an discernment all-in-one system based on face algorithm.
The utility model discloses a realize through following technical scheme: the utility model provides a discernment all-in-one system based on face algorithm which characterized in that: the system comprises a camera, wherein the camera is in wireless connection with a mobile phone client and a CMS client remote control system, and an SD card is arranged in the mobile phone client; the camera comprises an image shooting module, a face positioning module, an image preprocessing module, a face recognition module and a storage module, wherein the face positioning module, the image preprocessing module, the face recognition module and the storage module are connected with the image shooting module; the face positioning module comprises a face inspection module and a face registration module.
Preferably, the CMS client remote control system includes a log management module, a mobile detection setting module, a storage configuration module, a face detection setting module, a server configuration module, a linkage setting module, a defense period setting module, a face entry and a face library.
Preferably, the face recognition module comprises a face retrieval module, a face attribute recognition module, a face comparison module and a face living body module.
Preferably, the face recognition module is connected with the storage module.
Compared with the prior art, the utility model discloses an useful part is:
1. the system is suitable for face recognition under various environmental conditions, the face is intelligently detected and analyzed through dynamic videos, and the optimal face picture is ensured to be obtained through intelligent face exposure according to the environments of strong light, night vision, low illumination, sun backlight, hall backlight and low illumination backlight. Meanwhile, a deep learning intelligent face algorithm is embedded, and automatic detection, automatic tracking and automatic snapshot are carried out on the moving face; grading, screening, removing weight, and preferentially outputting a face picture most suitable for face recognition;
2. the utility model is used for face identification's camera 24 hours all can work a day, and first it does not infringe the right of the person, and second it is very safe, no matter indoor or outdoor all can use. The face recognition system means that the face of each person is attached with a name, and the face recognition camera cannot be seen by other people, but the monitoring system can be seen, the face recognition camera made by the face recognition technology is undoubtedly the best choice for identity recognition, the face can be found in real time from a monitoring camera image by adopting the rapid face detection technology, and the face can be compared with a face database in real time, so that the rapid identity recognition is realized.
Drawings
The present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a block diagram of the present invention;
fig. 2 is a block diagram of the face recognition module of the present invention;
fig. 3 is a block diagram of the CMS client remote control system according to the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be made with reference to the accompanying drawings.
As shown in fig. 1-2, a face algorithm-based all-in-one recognition machine system comprises a camera, wherein the camera is wirelessly connected with a mobile phone client and a CMS client remote control system; the camera comprises an image shooting module, a face positioning module, an image preprocessing module, a face recognition module and a storage module, wherein the face positioning module, the image preprocessing module, the face recognition module and the storage module are connected with the image shooting module; the face positioning module comprises a face inspection module and a face registration module. The face recognition module comprises a face retrieval module, a face attribute recognition module, a face comparison module and a face living body module. The face recognition module is connected with the storage module, and the CMS client remote control system comprises a log management module, a mobile detection setting module, a storage configuration module, a face detection setting module, a server configuration module, a linkage setting module, a defense period setting module, face input and a face library.
The utility model discloses get into the monitoring range of camera at the target and just can catch its clear facial photo to can trail and catch its facial photo, filter some photos that can not satisfy the quality requirement automatically wherein, compare the photo that accords with the quality requirement and the control list in the database, if reach predetermined similarity, the system can send out sound, light warning voluntarily, suggestion manual processing, preserves record information such as corresponding photo, time, passageway simultaneously. 3A (auto exposure, auto white balance, auto focus); image-based OSD menu, 16X digital zoom; the system can be remotely controlled through a mobile phone APP and a CMS client. An SD card is adopted to store a face library and a snapshot recognition record, and a Web end realizes the basic setting of face detection and local checking of the recognition record; the equipment side realizes human face living body detection and human face comparison, and stores comparison results in a local SD card; and the searching and deleting of the local identification record are supported, such as automatic deleting, manual deleting and the like. the utility model adopts HI3516DV300+ imx307 and living body recognition algorithm, and supports face tracking function, mobile detection function, direction detection function, flow statistic function, etc.; 2D/3D denoising function.
The system can realize the following human face operation.
(1) Face detection: detecting the position of a human face in an image; it is simply a "scanning" plus "decision" process. Firstly, scanning in the whole image range, and then judging whether the candidate regions are human faces one by one;
(2) face registration: and (5) positioning the coordinates of key points of the five sense organs on the face. The input of the face registration algorithm is 'one face image' and 'a face coordinate box', and the output is a coordinate sequence of key points of five sense organs. The number of key points of five sense organs is a preset fixed value.
(3) Identifying the face attribute: a technique for recognizing attribute values of a face such as gender, age, posture, expression, and the like. The method is applied to some cameras APP, and the characteristics of the sex, the age and the like of people in the camera view field can be automatically identified and marked.
(4) Face comparison: the human input two human face features are obtained by the human face feature extraction algorithm, and the output is the similarity between the two features.
(5) Face verification: the method comprises the steps of inputting two face features, obtaining the similarity of the two face features through face comparison, and verifying whether the two face features belong to the same person through comparison with a preset threshold value.
(6) Face recognition: inputting a face feature, and comparing the face feature with features corresponding to N identities registered in a library one by one to find out a feature with the highest similarity to the input feature.
(7) Face retrieval: the input human face is compared with the spoken human face in a set, and the human faces in the set are sorted according to the similarity after comparison;
(8) human face living body: it is determined whether the facial image is from a real person or an attacking prosthesis (photograph, video, etc.).
The system comprises a log management module, a mobile detection setting module, a storage configuration module, a face detection setting module, a server configuration module, a linkage setting module, a defense period setting module, face input and face library functions as follows:
a log management module: the IPC display system is used for displaying all operation information of the IPC, such as upgrading, restarting, alarming, connecting and the like;
the mobile detection setting module: the IPC alarm area and the sensitivity of triggering alarm are set;
a storage configuration module: the storage condition of the TF card of the equipment can be checked, and the TF card can be used for formatting the storage equipment;
face detection sets up the module: the selection of a face detection mode is realized, and detection parameter settings such as alarm temperature, identification threshold values and the like are set;
a server configuration module: the system is used for docking a remote server and establishing communication with a cloud attendance platform;
a linkage setting module: the method is used for setting IPC alarm type, alarm output mode, duration and the like;
a defense period setting module: and the method is used for setting the IPC alarm time period.
Face entry and face library: and locally importing the face data singly or in batch, and checking the face database data.
Identifying records: the snapshot record of the temperature measurement identification of the equipment can be inquired, derived and deleted according to conditions, and personnel can be added to the face database from the identification record.
Claims (4)
1. The utility model provides a discernment all-in-one system based on face algorithm which characterized in that: the system comprises a camera, wherein the camera is in wireless connection with a mobile phone client and a CMS client remote control system, and an SD card is arranged in the mobile phone client; the camera comprises an image shooting module, a face positioning module, an image preprocessing module, a face recognition module and a storage module, wherein the face positioning module, the image preprocessing module, the face recognition module and the storage module are connected with the image shooting module; the face positioning module comprises a face inspection module and a face registration module.
2. The human face algorithm-based all-in-one recognition machine system according to claim 1, characterized in that: the CMS client remote control system comprises a log management module, a mobile detection setting module, a storage configuration module, a face detection setting module, a server configuration module, a linkage setting module, a defense period setting module, a face input module and a face library module.
3. The human face algorithm-based all-in-one recognition machine system according to claim 1, characterized in that: the face recognition module comprises a face retrieval module, a face attribute recognition module, a face comparison module and a face living body module.
4. The human face algorithm-based all-in-one recognition machine system according to claim 1, characterized in that: the face recognition module is connected with the storage module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022816990.XU CN214151721U (en) | 2020-11-30 | 2020-11-30 | Recognition all-in-one machine system based on face algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022816990.XU CN214151721U (en) | 2020-11-30 | 2020-11-30 | Recognition all-in-one machine system based on face algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN214151721U true CN214151721U (en) | 2021-09-07 |
Family
ID=77567545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202022816990.XU Active CN214151721U (en) | 2020-11-30 | 2020-11-30 | Recognition all-in-one machine system based on face algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN214151721U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093050A (en) * | 2021-11-29 | 2022-02-25 | 深圳中维世纪科技有限公司 | Intelligent attendance system based on face recognition algorithm |
-
2020
- 2020-11-30 CN CN202022816990.XU patent/CN214151721U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093050A (en) * | 2021-11-29 | 2022-02-25 | 深圳中维世纪科技有限公司 | Intelligent attendance system based on face recognition algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934176B (en) | Pedestrian recognition system, recognition method, and computer-readable storage medium | |
| CN106991395B (en) | Information processing method and device and electronic equipment | |
| US9141184B2 (en) | Person detection system | |
| KR101781358B1 (en) | Personal Identification System And Method By Face Recognition In Digital Image | |
| CN110543867A (en) | crowd density estimation system and method under condition of multiple cameras | |
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| US20190019013A1 (en) | Facial recognition apparatus, recognition method and program therefor, and information device | |
| JP5669082B2 (en) | Verification device | |
| CN108932783A (en) | A kind of access control system towards big flow scene based on two-dimension human face identification | |
| CN110414381A (en) | Tracing type face identification system | |
| CN112949396B (en) | Self-adaptive method for searching for people on the same trip in scenic spot | |
| CN110458794B (en) | Quality detection method and device for accessories of rail train | |
| CN111914742A (en) | Attendance checking method, system, terminal equipment and medium based on multi-mode biological characteristics | |
| CN111079720B (en) | Face recognition method based on cluster analysis and autonomous relearning | |
| CN214151721U (en) | Recognition all-in-one machine system based on face algorithm | |
| CN112784740B (en) | Gait data acquisition and labeling method and application | |
| CN111241926A (en) | Attendance checking and learning condition analysis method, system, equipment and readable storage medium | |
| CN111259789A (en) | Face recognition intelligent security monitoring management method and system | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| CN109982051B (en) | Monitoring camera shooting method with animal identification function, monitoring camera and storage medium | |
| JP2009044526A (en) | Photographing device, photographing method, and apparatus and method for recognizing person | |
| CN115719428A (en) | Face image clustering method, device, equipment and medium based on classification model | |
| CN113591619A (en) | Face recognition verification device based on video and verification method thereof | |
| TW466452B (en) | Method and apparatus for photographing/recognizing a face | |
| CN110287841B (en) | Image transmission method and apparatus, image transmission system, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |