CN210442821U - Face recognition device - Google Patents
Face recognition device Download PDFInfo
- Publication number
- CN210442821U CN210442821U CN201921823323.5U CN201921823323U CN210442821U CN 210442821 U CN210442821 U CN 210442821U CN 201921823323 U CN201921823323 U CN 201921823323U CN 210442821 U CN210442821 U CN 210442821U
- Authority
- CN
- China
- Prior art keywords
- face
- module
- image
- recognition
- database
- 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
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The utility model provides a face recognition device, including image acquisition module, people's face collection module, people's face preprocessing module, face recognition module and people's face database. When the face recognition device is used, the image acquisition module acquires a head image of a user, and the face acquisition module extracts a face image of the user from the head image; the human face preprocessing module is used for carrying out posture correction and illumination correction on the human face; the face recognition module recognizes the preprocessed face and compares and matches the face with a face image prestored in a face database; the face database acquires and stores face images of users, wherein the face images are corrected through posture correction, illumination correction and the like, and successful matching is guaranteed.
Description
Technical Field
The utility model relates to a face identification technical field, in particular to face identification device.
Background
Face recognition technology has been widely used in video surveillance, bank account opening, door access and other industries. In the conventional technology, after a camera acquires a video stream, whether a face exists in a static image or not and whether the face is matched with an existing face database or not are analyzed frame by frame.
The existing face recognition device is easy to have the phenomenon of unsuccessful matching when the current face state of a user and a face image stored in a face database have larger changes.
SUMMERY OF THE UTILITY MODEL
The utility model aims at providing a face recognition device to solve the problem that current face recognition device can't discern the great face of change.
The utility model provides a face recognition device, which comprises an image acquisition module, a face preprocessing module, a face recognition module and a face database; the image acquisition module is used for shooting a head image of a user; the face acquisition module is used for extracting a face image of a user from the head image; the face preprocessing module is used for carrying out posture correction, illumination correction and other processing on the face; the face recognition module is used for recognizing the preprocessed face and comparing and matching the preprocessed face with a face image prestored in the face database; the face database is used for acquiring and storing face images of users.
When the face recognition device is used, the image acquisition module acquires a head image of a user, and the face acquisition module extracts a face image of the user from the head image; the human face preprocessing module is used for carrying out posture correction and illumination correction on the human face; the face recognition module recognizes the preprocessed face and compares and matches the face with a face image prestored in a face database; the face database acquires and stores face images of users, wherein the face images are corrected through posture correction, illumination correction and the like, and successful matching is guaranteed.
Further, the image acquisition module includes any one of a video camera or a video camera to acquire a picture or a video of the head of the user.
Further, the face acquisition module comprises a face detector, a feature point locator and a quality judgment sub-module, wherein the face detector is used for extracting the face image from the head image; the characteristic point positioner is used for calibrating the position of five sense organs in the face image, and the quality judgment submodule is used for detecting the pixel quality and the definition of the face image.
Furthermore, the face recognition module comprises a recognition sub-module and a comparison sub-module, and the comparison sub-module is connected with the face database.
Furthermore, the face recognition device further comprises a recognition result display module for displaying the recognition result of the face recognition module.
Furthermore, the face recognition device further comprises a processing module for processing data circulation among the image acquisition module, the face preprocessing module, the face recognition module and the face database.
Drawings
Fig. 1 is a schematic diagram of a module structure of a face recognition device according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of a module structure of a face recognition device according to a second embodiment of the present invention.
Description of the main element symbols:
| |
10 | |
40 | Recognition |
70 |
| |
20 | |
50 | ||
| |
30 | |
60 |
The following detailed description of the invention will be further described in conjunction with the above-identified drawings.
Detailed Description
In order to facilitate understanding of the present invention, the present invention will be described more fully hereinafter with reference to the accompanying drawings. Several embodiments of the invention are given in the accompanying drawings. The invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The utility model provides a face recognition device, which comprises an image acquisition module 10, a face acquisition module 20, a face preprocessing module 30, a face recognition module 40 and a face database 50; the image acquisition module 10 is used for shooting a head image of a user; the face acquisition module 20 is configured to extract a face image of the user from the head image; the face preprocessing module 30 is configured to perform posture correction, illumination correction, and the like on the face; the face recognition module 40 is configured to recognize a preprocessed face and compare and match the preprocessed face with a face image prestored in the face database; the face database 50 is used for acquiring and storing face images of users.
When the face recognition device is used, the image acquisition module 10 acquires a head image of a user, and the face acquisition module 20 extracts a face image of the user from the head image; the face preprocessing module 30 performs posture correction and illumination correction on the face; the face recognition module 40 recognizes the preprocessed face and compares and matches the face image with a face image prestored in a face database; the face database 50 acquires and stores a face image of the user, wherein the face image is corrected by posture correction, illumination correction, and the like, so as to ensure successful matching.
Specifically, the face recognition apparatus further includes a processing module 60, configured to process data flow among the image acquisition module 10, the face acquisition module 20, the face preprocessing module 30, the face recognition module 40, and the face database 50. The processing module 60 may be a general computer to implement the corresponding control processing process.
In particular, in an implementation, the image capturing module 10 may be any one of a video camera or a video camera, so as to capture a picture or a video of the head of the user.
Specifically, in this embodiment, the face acquisition module 20 includes a face detector, a feature point locator, and a quality determination sub-module, where the face detector is configured to extract the face image from the head image; the characteristic point positioner is used for calibrating the position of five sense organs in the face image, and the quality judgment submodule is used for detecting the pixel quality and the definition of the face image.
Specifically, the face recognition uses a camera or a video camera to acquire an image or a video stream containing a face, automatically detects and tracks the face in the image, and further performs a series of related application operations on the detected face image, including image acquisition, feature positioning, identity confirmation and search and the like technically. In brief, features in a human face, such as the height of eyebrows, the mouth corners and the like, are extracted from a human face image, and the result is output through comparison of the features, wherein the features are not changed or not changed even if the face is fat or thin. The influence of the face type fatness on the face identification result can be eliminated.
Specifically, in this embodiment, the face recognition module 40 includes a recognition sub-module and a comparison sub-module, and the comparison sub-module is connected to the face database 50. In face recognition, the recognition submodule finds out the approximate position of a face in a picture, the technology is relatively simple, a plurality of cameras have the face snapshot function, at present, a more reliable solution is a Histogram of Oriented Gradients (HOG), an algorithm capable of detecting the contour of an object, and the basic process is as follows: first we grayed the picture because the color information is not useful for face detection and it consumes computational resources, then analyze each pixel and its surrounding pixels, draw an arrow according to the brightness, the direction of the arrow represents the direction of gradual darkening of the pixel, if we operate each pixel repeatedly, the final pixel will be replaced by the arrow. These arrows are called gradients (gradients) which show the flow of the image from light to dark, and it is somewhat uneconomical for us to analyze each pixel, since it is too detailed, we may get lost in the ocean of the pixel, and we should observe the flow from a higher angle. It is not necessary to analyze every pixel, only a flow of light and dark from a higher viewing angle, for which the image is divided into small squares of 16x16 pixels. In each box, it is calculated how many shaves (how many points up, points up right, points right, etc.) are for each main direction. The original small square is then replaced by the directional arrow with the strongest directivity. Finally, we convert the original image into a very simple HOG representation that can easily capture the basic structure of the face, and in order to find the face in the HOG image, what needs to be done is the most similar part to what appears in some known HOG patterns. These HOG patterns are extracted from other face training data, and the face is captured.
After the facial feature data of the human face is obtained, the actual recognition process is not enough, the recognition accuracy is not high, and in order to solve the problem of the recognition accuracy, a deep convolutional neural network is usually trained to generate 128 measured values for the face, so that a machine finds out the measured values to be collected. Deep learning is more familiar to humans than which facial measurements are important. Each training is to observe three different facial images: a face training image of a known person is loaded, another photograph of the same person is loaded, and a photograph of another person is loaded to improve recognition accuracy. The algorithm then looks at the measurements it has generated for the three pictures. The neural network is then adjusted slightly to ensure that the measurements made by the first and second sheets are close, while the measurements made by the second and third sheets are slightly different. Through continuous adjustment of samples, the characteristic value of a certain face is finally generated after the steps are repeated for millions of times, and the face can be recognized very conveniently through the characteristic value. The data abstracts information such as human face, gender, age and the like, and obtains the most common data used by the computer, so that the computer can rapidly and conveniently perform processing such as comparison, storage, retrieval and the like. From there, the structured processing of the video data is completed. And the last step can be easily completed, the captured face photos are matched with the structured template data in the library one by one or matched with the structured template data of the characteristics after being structured, and the photos corresponding to the template data with the highest matching degree are found out.
Referring to fig. 2, a difference between the second embodiment and the first embodiment of the present invention is that in the second embodiment, the face recognition apparatus further includes a recognition result display module 70 for displaying the recognition result of the face recognition module 40, so that the user can know the comparison result.
The above-mentioned embodiments only represent some embodiments of the present invention, and the description thereof is specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that, for those skilled in the art, without departing from the spirit of the present invention, several variations and modifications can be made, which are within the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.
Claims (6)
1. A face recognition device is characterized by comprising an image acquisition module, a face preprocessing module, a face recognition module and a face database;
the image acquisition module is used for shooting a head image of a user;
the face acquisition module is used for extracting a face image of a user from the head image;
the face preprocessing module is used for carrying out posture correction and illumination correction on the face;
the face recognition module is used for recognizing the preprocessed face and comparing and matching the preprocessed face with a face image prestored in the face database;
the face database is used for acquiring and storing face images of users.
2. The face recognition apparatus of claim 1, wherein the image acquisition module comprises any one of a video camera or a video camera to acquire pictures or videos of the head of the user.
3. The face recognition apparatus according to claim 1, wherein the face acquisition module comprises a face detector, a feature point locator, and a quality judgment sub-module, the face detector is configured to extract the face image from the head image; the characteristic point positioner is used for calibrating the position of five sense organs in the face image, and the quality judgment submodule is used for detecting the pixel quality and the definition of the face image.
4. The face recognition apparatus of claim 1, wherein the face recognition module comprises a recognition sub-module and a comparison sub-module, and the comparison sub-module is connected to the face database.
5. The face recognition apparatus according to claim 1, further comprising a recognition result display module for displaying a recognition result of the face recognition module.
6. The face recognition apparatus of claim 1, further comprising a processing module for processing data flow between the image acquisition module, the face pre-processing module, the face recognition module, and the face database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921823323.5U CN210442821U (en) | 2019-10-28 | 2019-10-28 | Face recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921823323.5U CN210442821U (en) | 2019-10-28 | 2019-10-28 | Face recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210442821U true CN210442821U (en) | 2020-05-01 |
Family
ID=70411686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201921823323.5U Active CN210442821U (en) | 2019-10-28 | 2019-10-28 | Face recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210442821U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899436A (en) * | 2020-07-29 | 2020-11-06 | 北京市永康药业有限公司 | Intelligent chemical storage cabinet |
-
2019
- 2019-10-28 CN CN201921823323.5U patent/CN210442821U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899436A (en) * | 2020-07-29 | 2020-11-06 | 北京市永康药业有限公司 | Intelligent chemical storage cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | Face detection and recognition system using digital image processing | |
| US11176382B2 (en) | System and method for person re-identification using overhead view images | |
| US9818023B2 (en) | Enhanced face detection using depth information | |
| Zuo et al. | Real-time embedded face recognition for smart home | |
| JP5639478B2 (en) | Detection of facial expressions in digital images | |
| US6661907B2 (en) | Face detection in digital images | |
| KR101129405B1 (en) | Illumination detection using classifier chains | |
| US6292575B1 (en) | Real-time facial recognition and verification system | |
| CN109800643B (en) | Identity recognition method for living human face in multiple angles | |
| US20060110014A1 (en) | Expression invariant face recognition | |
| US20030059124A1 (en) | Real-time facial recognition and verification system | |
| CN111144366A (en) | Strange face clustering method based on joint face quality assessment | |
| CN111178252A (en) | Multi-feature fusion identity recognition method | |
| CN111178195A (en) | Facial expression recognition method and device and computer readable storage medium | |
| CN109190456B (en) | Multi-feature fusion overlook pedestrian detection method based on aggregated channel features and gray level co-occurrence matrix | |
| CN110991256A (en) | System and method for carrying out age estimation and/or gender identification based on face features | |
| CN111582118A (en) | Face recognition method and device | |
| CN210442821U (en) | Face recognition device | |
| Gangopadhyay et al. | FACE DETECTION AND RECOGNITION USING HAAR CLASSIFIER AND LBP HISTOGRAM. | |
| Guha | A report on automatic face recognition: Traditional to modern deep learning techniques | |
| Javidnia et al. | Palmprint as a smartphone biometric | |
| Thomas et al. | Real Time Face Mask Detection and Recognition using Python | |
| Amjed et al. | A robust geometric skin colour face detection method under unconstrained environment of smartphone database | |
| CN113052087A (en) | Face recognition method based on YOLOV5 model | |
| Tarunajaya et al. | Development of intelligent humanoid robot with face recognition features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |