Face Recognition Based on Normalization and the Phase Spectrum of the Local Part of an Image

Authors:
Jesus Olivares-Mercado;Kazuhiro Hotta;Haruhisa Takahashi;Hector Perez-Meana;Mariko Nakano Miyatake;Gabriel Sanchez-Perez
Affiliations:
Instituto Politecnico Nacional, ESIME Culhuacan, Col. San Francisco Culhuacan, Mexico D.F. Mexico 04430 and The University of Electro-Communications, Tokyo, Japan 182-8585;The University of Electro-Communications, Tokyo, Japan 182-8585;The University of Electro-Communications, Tokyo, Japan 182-8585;Instituto Politecnico Nacional, ESIME Culhuacan, Col. San Francisco Culhuacan, Mexico D.F. Mexico 04430;Instituto Politecnico Nacional, ESIME Culhuacan, Col. San Francisco Culhuacan, Mexico D.F. Mexico 04430;Instituto Politecnico Nacional, ESIME Culhuacan, Col. San Francisco Culhuacan, Mexico D.F. Mexico 04430
Venue:
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Year:
2008

Citing 6
Cited 0

Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
"Eigenphases vs. Eigenfaces"

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Face Recognition Algorithm Using the Discrete Gabor Transform

CONIELECOMP '07 Proceedings of the 17th International Conference on Electronics, Communications and Computers
Robust face recognition under partial occlusion based on support vector machine with local Gaussian summation kernel

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a robust faces recognition method based onthe Normalization and the Phase Spectrum of the Local Part ofan Image. The Principal Components Analysis (PCA) andthe Support Vector Machine (SVM) are used in theclassification stage. We evaluate how the proposed method is robustto illumination, occlusion and expressions using "AR FaceDatabase", which includes the face images of 109 subjects (60 malesand 49 females) under illumination changes, expression changes andpartial occlusion. The proposed method provides results with acorrect recognition rate more than 96.7%.