Face Recognition with Decision Tree-based Local Binary Patterns

Many state of the art face recognition algorithms use image descriptors based on Local Binary Pattern (LBP) features. We introduce and analyze a generalization
of LBP that uses the training data to obtain more discriminative LBP-like features. Since it is based on Decision Trees, we call it Decision Tree Local Binary Patterns (DTLBP). Preliminary tests on standard face recognition datasets show promising results.

Developed by Daniel Maturana at Group of Machine Intelligence, Department of Computer Science, Universidad Católica de Chile http://grima.ing.puc.cl

Category:

Science & Technology

Tags:

• Face Recognition
• LBP