CN205621093U - Access control system based on face identification - Google Patents

Abstract

The utility model relates to an access control system based on face recognition, and relates to the technical field of computer science; it includes a camera, an ARM development board, and an RFID card reader; the camera is connected to the ARM development board, and the RFID card reader is connected to the ARM development board. Using face recognition technology and RFID recognition technology, under the Ubuntu system, with the help of OpenCV's powerful visual processing capabilities, a face recognition system based on an embedded platform is designed and implemented to double-verify the identity of personnel to ensure the safety of import and export .

Description

Access control system based on face recognition

technical field

The utility model relates to the field of computer science and technology, in particular to an access control system based on face recognition.

Background technique

After years of research and development of face recognition, many research results have been obtained, but most of the face recognition systems are based on PC architecture, and their portability and mobility are greatly limited. However, in some special applications (such as intelligent communities, outdoor non-control point personnel monitoring, etc.), it will be very inconvenient to use. People have put forward new requirements for face recognition application systems, and the research on face recognition in embedded systems has a strong reality. Significance and broad application prospects. Although many domestic companies have launched access control systems and time attendance systems based on embedded face recognition at this stage, most of these embedded face recognition systems are still based on PC architecture. The implementation of the face recognition algorithm is still completed on the background PC. With the development of computer hardware technology, embedded systems have become an important branch of the computer field. The performance of embedded microprocessors and embedded operating systems has been continuously improved, which has laid a good foundation for the research of embedded face recognition systems.

Traditional RFID access control Traditional access control systems mostly use identification and authentication methods such as mechanical locks and swiping cards, requiring personnel to operate with cards at close range. As well as the hidden dangers of misappropriation and high costs.

Utility model content

The purpose of this utility model is to provide a simple in structure, reasonable in design, easy to use access control system based on face recognition for the defect and insufficiency of prior art, utilize face recognition technology and RFID recognition technology, under Ubuntu system, With the help of OpenCV's powerful visual processing capabilities, a face recognition system based on an embedded platform is designed and implemented, which double-authenticates the identity of personnel to ensure the safety of import and export.

For achieving the above object, the technical scheme that the utility model adopts is: it comprises camera, ARM development board, RFID card reader; Camera is connected with ARM development board, and RFID card reader is connected with ARM development board.

The camera mentioned is Vimicro ZC301P camera.

The ARM development board described is a Tiny6410ARM development board.

The RFID card reader is an RS232 read-write card reader.

The ARM development board is mainly used for RFID identity verification, video reading, training classifier and detection of faces, face database establishment, face recognition and other main functions; wherein, the RFID identity verification is carried by the user RFID card for identity verification; the training classifier is to learn a classification function or construct a classification model (that is, what we usually call a classifier (Classifier)) on the basis of existing face samples. Or the model can map the data records in the face database to the recognition object, thereby carrying out face detection; the described detection face is to classify the classifier used for the video image collected by the camera, and detect the face information therein ; The establishment of the face database is to establish a relevant face database for the people to be identified, first carry out normalization processing to the collected face images, extract the observation vector from the image, set up the HMM model and save Relevant data: The described face recognition is to identify the newly collected face images, and find the most similar one in the face database.

After adopting the above-mentioned structure, the beneficial effects of the utility model are: the access control system based on face recognition described in the utility model utilizes face recognition technology and RFID recognition technology, under the Ubuntu system, with the help of the powerful visual processing ability of OpenCV, the design And the face recognition system based on the embedded platform is realized, and the identity of the personnel is double-verified to ensure the safety of import and export. The utility model has the advantages of simple structure, reasonable setting, and low production cost.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are only some embodiments of the utility model, and those skilled in the art can also obtain other drawings according to these drawings without any creative effort.

Fig. 1 is a structural representation of the utility model.

Fig. 2 is a working principle diagram of the utility model.

Fig. 3 is a working principle diagram of the EFID card reader in the utility model.

Fig. 4 is a working principle diagram of the camera in the utility model.

Explanation of reference signs:

Camera 1, ARM development board 2, RFID card reader 3.

detailed description

Below in conjunction with accompanying drawing, the utility model is further described.

Referring to Fig. 1-shown in Fig. 4, the technical scheme that this specific embodiment adopts is: it comprises camera 1, ARM development board 2, RFID card reader 3; Camera 1 is connected with ARM development board 2, RFID card reader 3 Connect with ARM development board 2.

Described camera 1 is Vimicro ZC301P camera.

The ARM development board 2 is a Tiny6410ARM development board, and the system is an Ubuntu system with built-in OpenCV.

The RFID card reader 3 is an RS232 read-write card reader.

Described ARM development board 2 is mainly used in the operation of main functions such as RFID identity verification, video reading, training classifier and detection face, face database establishment, face recognition; Wherein, described RFID identity verification is to the user carry RFID card for identity verification; the training classifier is to learn a classification function or construct a classification model (that is, what we usually call a classifier (Classifier)) on the basis of existing face samples. The function or model can map the data records in the face database to the recognition object, thereby carrying out face detection; the described detection face is to classify the classifier used for the video image collected by the camera, and detect the face in it information; the establishment of the described face database is to establish a relevant face database for the person to be identified, first carry out normalization processing on the collected face images, extract the observation vector from the image, set up the HMM model and Preserve relevant data; Described face recognition is to recognize newly collected face images, and finds the most similar one in the face database.

The workflow of this embodiment is as follows:

1. Swipe the card, and then the system will compare the read card number with the system. If the card number is correct, the RFID verification is over, otherwise the system will prompt the user to verify the identity again, and the verification must continue;

2. Use the classifier training on the ARM development board 2. When using the PCA algorithm for face detection, in order to obtain a cascaded classifier, it is necessary to use the Harr feature of the face sample data for classification. OpenCV has an excellent Classifier training tool, users can also train their own classifiers according to actual needs;

3. Video capture, the process of video capture: first turn on the camera device, set the video format, then initialize and judge whether the camera is turned on by the number of cameras, and finally acquire and process the image;

4. Face detection. Face detection is the basis of the entire face recognition. The system first detects the image recognized by the camera, and saves the detected face image to the face database;

5. The face library is established. After the face image library is established, it is necessary to perform HMM training on the images in the image library to create a unique HMM for each person;

6. Face recognition. The process of face recognition is to calculate the similarity of the detected faces and output the one with the highest similarity. Therefore, the user can set a similarity threshold. If the similarity is greater than this threshold, then It is considered to identify the person, otherwise the person cannot be identified.

After adopting the above-mentioned structure, the beneficial effects of the utility model are: the access control system based on face recognition described in the utility model utilizes face recognition technology and RFID recognition technology, under the Ubuntu system, with the help of the powerful visual processing ability of OpenCV, the design And the face recognition system based on the embedded platform is realized, and the identity of the personnel is double-verified to ensure the safety of import and export. The utility model has the advantages of simple structure, reasonable setting, and low production cost.

The above is only used to illustrate the technical solution of the utility model without limitation, other modifications or equivalent replacements made by those skilled in the art to the technical solution of the utility model, as long as they do not depart from the spirit and scope of the technical solution of the utility model , should be covered in the scope of the claims of the present utility model.

Claims (4)

1. gate control system based on recognition of face, it is characterised in that: it comprises photographic head, ARM development board, RFID card reader；Photographic head is connected with ARM development board, and RFID card reader is connected with ARM development board.

Gate control system based on recognition of face the most according to claim 1, it is characterised in that: described photographic head is Vimicro ZC301P photographic head.

Gate control system based on recognition of face the most according to claim 1, it is characterised in that: described ARM development board is Tiny6410ARM development board.

Gate control system based on recognition of face the most according to claim 1, it is characterised in that: described RFID card reader is RS232 read-write type card reader.