Check patentability & draft patents in minutes with Patsnap Eureka AI!

Face identification method based on maximum stable extremum area

A maximum stable extreme value, face recognition technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of face recognition accuracy interference, changing hairstyles, keeping beards, etc., to achieve good adaptability , fast running, functional and practical effects

Inactive Publication Date: 2013-04-17
TIANJIN YAAN TECH CO LTD
View PDF3 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, in real life, human faces often wear various decorations, such as glasses, masks, scarves, hats; or change hairstyles, grow beards, make-up; Deep-set eyebrows, etc.; these random and elastic face changes are bound to bring great interference to the accuracy of face recognition

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
  • Face identification method based on maximum stable extremum area
  • Face identification method based on maximum stable extremum area
  • Face identification method based on maximum stable extremum area

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0029] In recent years, the field of computer vision has made significant progress in the study of image local invariant features, and its results have greatly promoted the development of image registration related technologies. In 2002, Matas et al. proposed a segmentation algorithm similar to the watershed algorithm to extract the MSER (Maximally Stable Extremal regions) with good affine invariance in the image. The MSER feature area has good affine invariance, good stability, high reproducibility, and good robustness to illumination, viewing angle, and partial occlusion. Due to its special extraction process, MSER is also resistant to scale changes. It has certain adaptability.

[0030] In order to achieve feature matching, it is necessary to describe the detected features. In 2005, Krystian Mikolajczyk proposed a scale and affine invariant interest point detect...

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 face identification method based on a maximum stable extremum area. The invention provides the face identification method based on the maximum stable extremum area. The method comprises the steps of: acquiring the maximum stable extremum area of a face as key characteristics of face identification; extracting the attributes representing the key characteristic and classifying the key characteristics; and judging the similarity of face images according to the attributes of the key characteristics of face image and the face image so as to identify the face. The face identification method provided by the invention has great robustness aiming at factors such as scale, affine transform, illumination variation, rotation, face expression change, and noise, and has a certain identifying capacity to faces under complex backgrounds and shielded faces.

Description

technical field [0001] The invention relates to the technical field of pattern recognition and image processing, in particular to a face recognition method based on the maximum stable extremum region. Background technique [0002] The current biometric recognition technologies mainly include: fingerprint recognition, retina recognition, iris recognition, hand shape recognition, palmprint recognition, face recognition, etc. Compared with other recognition methods, face recognition has the characteristics of naturalness, intuition, low cost, simple use, easy operation and high stability, so it has been widely researched and applied. From ancient times to the present, when human beings confirm a person's identity, they generally judge by their face. This fact provides a theoretical basis and practical basis for the emergence of the concept of face recognition. [0003] Since the "9.11" terrorist attack in the United States in 2001, countries around the world have generally car...

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
IPC IPC(8): G06K9/00G06K9/62
Inventor 张藻张羽
Owner TIANJIN YAAN TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com