Face recognition with multi-scale block local ternary patterns

Authors:
Lian Zhu;Yan Zhang;Changyin Sun;Wankou Yang
Affiliations:
School of Automation, Southeast University, Nanjing, China;The Third Research Institute of Ministry of Public Security, Shanghai, China;School of Automation, Southeast University, Nanjing, China;School of Automation, Southeast University, Nanjing, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 5
Cited 0

Face Recognition System Using Local Autocorrelations and Multiscale Integration

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
Acquiring Linear Subspaces for Face Recognition under Variable Lighting

IEEE Transactions on Pattern Analysis and Machine Intelligence
Capitalize on Dimensionality Increasing Techniques for Improving Face Recognition Grand Challenge Performance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning multi-scale block local binary patterns for face recognition

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel approach to face recognition, called Multi-scale Block Local Ternary Patterns (MB-LTP), which considers both local and various scale texture information to represent face images. In MB-LTP, we compare average values of sub-regions and use a 3-valued codes method to get the MB-LTP value. The MB-LTP histograms are then extracted and concatenated into a single, spatially enhanced feature vector representing the face image in recognition. We use a nearest neighbor classifier in the computed feature space with Chi square as a dissimilarity measure. MB-LTP code presents several advantages: (1)It is more robust than LBP;(2)it is more discriminative and less sensitive to noise;(3)it encodes not only microstructures but also macrostructures of image patterns. Experiments on ORL and AR databases show that the proposed MB-LTP method significantly outperforms other LBP based face recognition algorithms.