Learning Discriminative Local Binary Patterns for Face Recognition. Maturana, D., Mery, D., & Soto, A. In 9th IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2011.
Learning Discriminative Local Binary Patterns for Face Recognition [pdf]Paper  abstract   bibtex   17 downloads  
Histograms of Local Binary Patterns (LBPs) and variations thereof are a popular local visual descriptor for face recognition. So far, most variations of LBP are designed by hand or are learned with non-supervised methods. In this work we propose a simple method to learn discriminative LBPs in a supervised manner. The method represents an LBP-like descriptor as a set of pixel comparisons within a neighborhood and heuristically seeks for a set of pixel comparisons so as to maximize a Fisher separability criterion for the resulting his- tograms. Tests on standard face recognition datasets show that this method can create compact yet discriminative descriptors.

Downloads: 17