Face recognition method based on dynamic threshold local binary pattern

Authors:
Weisheng Li;Peng Fu;Lifang Zhou
Affiliations:
Chongqing University of Posts and Telecommunications Chongqing, China;Chongqing University of Posts and Telecommunications Chongqing, China;Chongqing University of Posts and Telecommunications Chongqing, China
Venue:
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Year:
2012

Citing 8
Cited 0

From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
The CMU Pose, Illumination, and Expression (PIE) Database

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Face Description with Local Binary Patterns: Application to Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time Stereo Face Recognition by Fusing Appearance and Depth Fisherfaces

Journal of VLSI Signal Processing Systems
Enhanced local texture feature sets for face recognition under difficult lighting conditions

IEEE Transactions on Image Processing
Multi-scale local binary pattern histograms for face recognition

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

Quantified Score

Hi-index	0.00

Visualization

Abstract

As the traditional LBP algorithm only considers the single threshold characteristics without using the relationship between the threshold and the neighbor pixels, the useful characteristics will be lost. In this paper a method of face recognition based on Dynamic Threshold Local Binary Pattern (DTLBP) is proposed. In DTLBP the binary digit is encoded with a dynamic threshold, which is adjusted by the relationship of neighborhood pixels gray value and the central pixel gray value. The DTLBP method, proposed by this paper, uses dynamic threshold to encode, and computes the statistic histogram referring to the work in LBP method. Finally, the experimental results based on Yale B, CMU PIE and ORL face databases show that the method is superior to the traditional LBP and LTP method.