Non-contact human face identifying algorithm based on expanded eight-domain local texture features and attendance system

A texture feature, face recognition technology, applied in the field of non-contact face recognition algorithm and check-in system

Active Publication Date: 2013-05-01
西安电子科技大学青岛计算技术研究院
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although different methods have their own advantages and disadvantages under different conditions, the most fundamental problem in face recognition is the need for efficient and highly discriminative feature descriptors for face features.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-contact human face identifying algorithm based on expanded eight-domain local texture features and attendance system
  • Non-contact human face identifying algorithm based on expanded eight-domain local texture features and attendance system
  • Non-contact human face identifying algorithm based on expanded eight-domain local texture features and attendance system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The invention builds a computer-based sign-in system integrating intelligent image collection and face recognition. System block diagram see figure 1 , the system is divided into foreground and background two parts. The front desk is mainly composed of a display installed on the front panel, a camera, a two-channel speaker, and a pressure sensor on the ground. The pressure sensor is about 0.5 meters away from the front panel. The background is composed of a computer host. All devices in the foreground establish data connections with the host in the background.

[0033] The functions of each device: the pressure sensor is used to detect whether someone comes to sign in; the camera is used to take the front face image of the sign-in person (the algorithm of the present invention can withstand small-angle face deflection); the speaker and the display are used to output prompt information.

[0034] The core of the present invention lies in the face recognition algorithm,...

Embodiment 2

[0070] Preparations before system operation: After building the hardware of the entire system and before the entire system is put into operation, the user needs to collect the face image information of all employees. And mark the identity information to build an employee face database. Then our algorithm will build a face feature library based on the database. The established feature library can be directly input into the classifier when the system is working, instead of re-extracting features from the employee face database, so that the real-time operation of the system can be guaranteed. sex.

[0071] Flow process and method of use when the system works: after the preparatory work is completed, the system of the present invention can be operated, and the specific steps are as follows:

[0072] 1) When employees go to work, face the camera and stand on the cover above the pressure sensor.

[0073] 2) The pressure sensor generates a pulse signal and transmits it to the host ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a non-contact human face identifying algorithm based on expanded eight-domain local texture features and an attendance system. The algorithm comprises the following steps of 1, extracting the expanded eight-domain local texture features of a human-face image, wherein the step comprises three stages, i.e. an image point marking stage, an image point encoding state and an image feature vector extracting stage; and 2, classifying the extracted local texture features by using an SVM (support vector machine) classifier, so that a human face is identified. The invention provides an expanded eight-domain local texture feature descriptor, which can describe the texture features in eight directions of a local region, and after identification rate of methods on an ORL (Optical Return Loss) database, an AR database and an FERET (Face Recognition Technology) database are compared, the obtained result shows that the descriptor provided by the invention is better than the other methods and particularly, the improved scheme has higher robustness.

Description

technical field [0001] The invention belongs to the field of pattern recognition and computer vision, and relates to a non-contact face recognition algorithm and a sign-in system based on extended eight-neighborhood local texture features. Background technique [0002] With the advancement of computer technology, artificial intelligence and pattern recognition technology have developed rapidly, and biometric technology has become a research hotspot. It is a technology that uses human biometrics for identity authentication. Compared with traditional identity authentication technologies, biometrics-based identity authentication technology has the following characteristics: not easy to forget or lose; good anti-counterfeiting performance, not easy to forge or be stolen; carry , available anytime, anywhere. Biometrics mainly includes face recognition, fingerprint recognition, palmprint recognition, expression recognition, iris recognition, retina recognition, voice recognition,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
Inventor 赵恒王小平张春晖
Owner 西安电子科技大学青岛计算技术研究院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap