BROWSE
Detail
Conference Paper
Robust Face Recognition Using The Modified Census Transform
Cited 5 time in 
Share 
Share
- Authors
- Woo-Han Yun, Ho-Sub Yoon, Do-Hyung Kim, Su-Young Chi
- Issue Date
- 2007-10
- Citation
- International Symposium on Communications and Information Technology (ISCIT) 200, pp.749-752
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Many algorithms do not work well in real-world systems as real-world systems have problems with illumination variation and imperfect detection of face and eyes. In this paper, we compare the illumination normalization methods (SQI, HE, GIC), and the feature extraction methods (PCA, LDA, 2dPCA, 2dLDA, B2dLDA) using Yale B database and ETRI database. In addition, we propose a stable and robust illumination normalization method using a modified census transform. The experimental results show that MCT is robust for illumination variations as well as for inaccurate eyes and face detections. B2dLDA was shown to have the best performance in the feature extraction methods. © 2007 IEEE.
- KSP Keywords
- Best performance, Census Transform, Illumination Normalization, Illumination variations, Imperfect detection, Normalization method, Real-world, Robust face recognition, Yale B Database, feature extraction method