TY - GEN
T1 - A study on partial face recognition of eye region
AU - Teo, Chuan Chin
AU - Neo, Han Foon
AU - Teoh, Andrew Beng Jin
PY - 2007
Y1 - 2007
N2 - In this preliminary study, we have investigated the human eye as an important part of face for personal authentication under certain restricted circumstances related to face occlusion, individual privacy concerns and religious practices. Although this part of face is not as unique as full-face, but it offers much higher computational efficiency with minimum processing steps, and minimum storage capacity as compared to full-face. In our experiments, the frontal human eye images are generated from Essex dataset with 153 subjects. The images are tested with non-negative matrix factorization (NMF), local NMF (LNMF) and spatially confined NMF (SFNMF) respectively. Our experiments show that LNMF performs most optimally to attain 95.12% recognition rate, follow by SFNMF and NMF, which achieve 94.48% and 93.23%, respectively. It is evidenced that LNMF and SFNMF performs better than sole plain NMF. Besides, another goal of this paper is to study the influence of r, to which degree the basis number is sufficient to achieve the optimal recognition rate.
AB - In this preliminary study, we have investigated the human eye as an important part of face for personal authentication under certain restricted circumstances related to face occlusion, individual privacy concerns and religious practices. Although this part of face is not as unique as full-face, but it offers much higher computational efficiency with minimum processing steps, and minimum storage capacity as compared to full-face. In our experiments, the frontal human eye images are generated from Essex dataset with 153 subjects. The images are tested with non-negative matrix factorization (NMF), local NMF (LNMF) and spatially confined NMF (SFNMF) respectively. Our experiments show that LNMF performs most optimally to attain 95.12% recognition rate, follow by SFNMF and NMF, which achieve 94.48% and 93.23%, respectively. It is evidenced that LNMF and SFNMF performs better than sole plain NMF. Besides, another goal of this paper is to study the influence of r, to which degree the basis number is sufficient to achieve the optimal recognition rate.
UR - http://www.scopus.com/inward/record.url?scp=49649105255&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=49649105255&partnerID=8YFLogxK
U2 - 10.1109/ICMV.2007.4469271
DO - 10.1109/ICMV.2007.4469271
M3 - Conference contribution
AN - SCOPUS:49649105255
SN - 9781424416257
T3 - Proceedings - International Conference on Machine Vision, ICMV 2007
SP - 46
EP - 49
BT - Proceedings - International Conference on Machine Vision, ICMV 2007
T2 - International Conference on Machine Vision, ICMV 2007
Y2 - 28 December 2007 through 29 December 2007
ER -