Back to articles
Articles
Volume: 31 | Article ID: art00007
Image
Face Recognition by the Construction of Matching Cliques of Points
Fred Stentiford
  DOI :  10.2352/ISSN.2470-1173.2019.8.IMAWM-404  Published Online :  January 2019
Abstract

This paper addresses the problem of face recognition using a graphical representation to identify structure that is common to pairs of images. Matching graphs are constructed where nodes correspond to local brightness gradient directions and edges are dependent on the relative orientation of the nodes. Similarity is determined from the size of maximal matching cliques in pattern pairs. The method uses a single reference face image to obtain recognition without a training stage. Results on samples from MegaFace obtain a 100% correct recognition result.

Journal Title : Electronic Imaging
Publisher Name : Society for Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151 USA
Subject Areas :
Views 24
Downloads 1
 DOI 10.2352/ISSN.2470-1173.2019.8.IMAWM-404
 articleview.views 24
 articleview.downloads 1
  Cite this article 

Fred Stentiford, "Face Recognition by the Construction of Matching Cliques of Points"  in Proc. IS&T Int’l. Symp. on Electronic Imaging: Imaging and Multimedia Analytics in a Web and Mobile World,  2019,  pp 404-1 - 404-5,  https://doi.org/10.2352/ISSN.2470-1173.2019.8.IMAWM-404

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2019
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA
10.2352/ISSN.2470-1173.2019.8.IMAWM-404
2470-1173(20190113)2019:8L.4041;1-
ei_24701173_v2019n8_r1/s6.xml
/ist/ei/2019/00002019/00000008/art00007
Articles
Face Recognition by the Construction of Matching Cliques of Points
StentifordFred
13012019
2019
8
404-1
404-5
2019
This paper addresses the problem of face recognition using a graphical representation to identify structure that is common to pairs of images. Matching graphs are constructed where nodes correspond to local brightness gradient directions and edges are dependent on the relative orientation of the nodes. Similarity is determined from the size of maximal matching cliques in pattern pairs. The method uses a single reference face image to obtain recognition without a training stage. Results on samples from MegaFace obtain a 100% correct recognition result.
Face recognitionpattern recognitionsimilarityhuman visiongraph matching