Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-directional multi-level double-cross robustness identification based on face structure features

A double-cross robustness and recognition method technology, which is applied in the field of multi-directional and multi-level double-cross robust recognition based on face structural features, can solve problems such as data error, large amount of calculation, and slow down of face recognition speed , to maximize the image signal-to-noise ratio, simplify the algorithm steps, and reduce the effect of classification error

Inactive Publication Date: 2017-07-21
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the existing traditional algorithms have significant individual differences due to the influence of many appearance factors of facial images when performing feature extraction. Appearance factors such as illumination changes, posture changes, occlusion, image blur and expression changes, etc. It is difficult to improve the accuracy rate; in addition, the amount of calculation of the existing face recognition is still huge, which slows down the speed of face recognition. This delay often brings great errors to the data, and the system gives people an unfriendly feeling

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
  • Multi-directional multi-level double-cross robustness identification based on face structure features
  • Multi-directional multi-level double-cross robustness identification based on face structure features
  • Multi-directional multi-level double-cross robustness identification based on face structure features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0037] In specific implementation, figure 1 It is the flow of the multi-directional multi-level double-crossover robust recognition method based on the structural features of the face. The input face image H(x k ,y k ), H(x k ,y k ) is a grayscale image, and the face image training set P k :{P k |1,...,M}, where M is the total number of image samples in the training set, k is an integer and 1≤k≤M; let the distance between the two eyes of the input face image be d, and take the midpoint of the two eyes as the coordinate The origin is O(0, 0), and the coordinates of the left and right eyes are (-0.5d, 0) and (0.5d, 0) respectively.

[0038] For the above-mentioned face image whose coordinate values ​​have been marked, take O as the reference, and take the left and right distance O as d, and take 0.5d in the upper direction and 1.5d in the lower...

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 multi-directional multi-level double-cross robustness identification based on face structure features. The method being a novel method for extracting face expression features mainly studies two main components of face recognition: face representation extraction and face matching. Face representation is extracted by means of double-crossed two-group-dividing coding in eight directions of an inner circle and an outer circle, so that face features are summarized comprehensively and the computing load is reduced. Multi-directional gradient filtering and multi-level face representation are added and a gray-scale face image is transformed into a multi-directional gradient image by using a Gaussian first-order operator derivative, so that influences caused by illumination, image blurring, shielding, attitudes, and expressions can be reduced and thus robustness of illumination changing can be enhanced. According to a three-criterion optimal gradient filter, SNR maximization, edge positioning precision keeping, and single edge response are realized, so that the interference during face expression extraction can be reduced and thus face expression features can be extracted accurately and the computing cost can be saved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-directional and multi-level double-cross robust recognition method based on human face structural features. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. [0003] The research on the face recognition system began in the 1960s. After the 1980s, it was improved with the development of computer technology and optical imaging technology, and it really entered the primary application stage in the late 1990s. Technology implementation is the main focus; the key to the success of...

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): G06K9/00G06K9/40G06K9/42G06K9/46
CPCG06V40/171G06V10/32G06V10/30G06V10/443
Inventor 樊小萌陈志岳文静黄雅楠李熠
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com