Robust Recognition via Information Theoretic Learning

This Springer Brief represents a comprehensive review of information theoretic methods for robust recognition. A variety of information theoretic methods have been proffered in the past decade, in a large variety of computer vision applications; this work brings them together, attempts to impart the theory, optimization and usage of information entropy.

The authors resort to a new information theoretic concept, correntropy, as a robust measure and apply it to solve robust face recognition and object recognition problems. For computational efficiency, the brief introduces the additive and multiplicative forms of half-quadratic optimization to efficiently minimize entropy problems and a two-stage sparse presentation framework for large scale recognition problems. It also describes the strengths and deficiencies of different robust measures in solving robust recognition problems.

• Face recognition
• information theoretic learning
• large scale
• robust estimation
• sparse representation

• National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China

  Ran He, Baogang Hu

• School of Information and Control, Nanjing University of Information Science and Technology, Nanjing, China

  Xiaotong Yuan

• Institute of Automaton Chinese Academy of Sciences, Beijing, China

  Liang Wang

Policies and ethics