Everyone loves Local Binary Patterns! They're so simple and effective. But their basic parameters were pretty much hand-picked by their creator; I wondered if it was possible to learn a better Local Binary Pattern-like descriptor using supervised data. Since this was before everyone went crazy for Deep Learning, I came up with a scheme using tree-structured or fern-structured quantizers that had vanilla Local Binary Patterns as a special case. The basic insight is that a tree (or list, in the case of ferns) of binary decisions can be seen as mapping to a feature space consisting of binary strings.

• L. Caro, J. Correa, P. Espinace, D. Maturana, R. Mitnik, S. Montabone, S. Pszszolkowski, D. Langdon, A. Araneda, D. Mery, M. Torres, and A. Soto. Indoor Mobile Robotics at GRIMA, PUC. Journal of Intelligent and Robotic Systems, 2011. [ .bib ]
• D. Maturana, D. Mery, and A. Soto. Learning Discriminative Local Binary Patterns for Face Recognition. In Ninth IEEE International Conference on Automatic Face and Gesture Recognition (FG). 2011. [ .bib ] [  .pdf ]
• D. Maturana, D. Mery, and A. Soto. Face Recognition with Decision Tree-Based Local Binary Patterns. In Tenth Asian Conference in Computer Vision (ACCV). 2010. [ .bib ] [  .pdf ] [  poster ]
• D. Maturana, D. Mery, and A. Soto. Face Recognition with Local Binary Patterns, Spatial Pyramid Histograms and Naive Bayes Nearest Neighbor Classification. In SCCC 2009. 2009. URL: http://doi.ieeecomputersociety.org/10.1109/SCCC.2009.21. [ .bib ]