Feedback and inquiries

Machine Vision Group
Department of Electrical and Information Engineering P.O.Box 4500
FIN-90014 University of Oulu
Finland
Tel. +358-8-553 1011
Fax. +358-8-553 2612

Local Binary Pattern

The local binary pattern (LBP) texture analysis operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. The current form of the LBP operator is quite different from its basic version: the original definition is extended to arbitrary circular neighbourhoods, and a number of extensions have been developed. The basic idea is however the same: a binary code that describes the local texture pattern is built by thresholding a neighbourhood by the gray value of its center.

Through its recent extensions, the LBP operator has been made into a really powerful measure of image texture, showing excellent results in terms of accuracy and computational complexity in many empirical studies. The LBP operator can be seen as a unifying approach to the traditionally divergent statistical and structural models of texture analysis.

 Local Binary Pattern on three orthogonal planes (LBP-TOP)

LBP-TOP is an extension of the LBP operator, which combines both motion and appearance. It has been successfully applied to the face expression recognition, dynamic texture recognition, dynamic texture segmentation and synthesis.