20060411 face recognition using face arg matching


Published on

Face Recognition Using Face-ARG Matching

Published in: Technology
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

20060411 face recognition using face arg matching

  1. 1. Face Recognition Using Face-ARG Matching Bo-Gun Park, Kyoung-Mu Lee, Member, IEEE, and Sang-Uk Lee, Member, IEEE Zheng-Wen Shen 2006/04/11IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINEINTELLIGENCE, VOL. 27, NO. 12, DECEMBER 2005 1
  2. 2. Outline1. Introduction2. The description of the Face-ARG3. The Correspondence Graph4. Similarity between two Face-ARGs and Face Recognition5. Experimental Results6. Conclusion 2
  3. 3. 1. Introduction A set of simple lines characterizing the structure of an object are sufficient to identify its shape and recognizable as gray-level images A face is represented by the Face-ARG model  All the geometric quantities and the structural information are encoded in an Attributed Relational Graph  A set of nodes (line features) and binary relations between them 3
  4. 4. Two-phases1. The correspondence graph of the reference Face-ARG and the test Face- ARG is constructed using the partial ARG matching algorithm through the stochastic analysis of the feature correspondence in the relation vector space.2. The stochastic distance between the corresponding relation vector spaces of the extracted subgraphs is evaluated and compared for the identification of a face. 4
  5. 5. An example of the Face-ARGrepresentation and partial matching 5
  6. 6. 2. The description of the Face-ARG An ordered triple Face-ARG model defined as: V = {V1,…,VN} R ={rij} F ={Ri|i=1,…,N} Ri = {rij|j=1,..,N, j<>i} 6
  7. 7. 3. The Correspondence Graph Assume that two Face-ARGs, G1 and G2 are given by 7
  8. 8. A Correspondence Graph A correspondence graph between G1 and G2: 8
  9. 9. A correspondence graph between G1and G2 9
  10. 10. Block diagram and data flows for thepartial ARG matching process. 10
  11. 11. 4. Similarity between two Face-ARGsand Face Recognition Similarity between Two Face-ARGs 11
  12. 12.  Face Recognition  Select the best matched identity among the database which gives the highest similarity value above some prespecified threshold as the final recognition. 12
  13. 13. 5. Experimental Results For the evaluation of the proposed algorithm’s performance, it was tested on the AR face DB, which is composed of color images of 135 people (76 men and 59 women). The AR face DB includes frontal view images with different facial expressions, illumination conditions, and occlusion by sunglasses and scarf. All images used for experiments were normalized to face images of 120 by 170 pixels. 13
  14. 14. The ARG face database 14
  15. 15. Analysis on the Effect of imprecise lineextraction Imprecise line extraction or noise can affect the overall performance of the line feature-based face recognition algorithms  Position error  Loss of line segments  broken line segments 15
  16. 16. Examples of feature variations due tothe imprecise line extraction. Position error Missing lines broken lines 16
  17. 17. Position error 17
  18. 18. Missing lines 18
  19. 19. Broken lines 19
  20. 20. Recognition Results on the Real Face DB 20
  21. 21. 6. Conclusion 21