Rotation-invariant local binary pattern texture classification
Niraj P. Doshi, Gerald Schaefer · Proceedings ELMAR-2012 · 2012
Texture analysis and classification is a well researched topic in computer vision. Since textures are captured at arbitrary angles, the derivation of rotation-invariant texture descriptors has received much attention. A group of high performing texture algorithms are based on the concept of local binary patterns (LBP). These algorithms are very efficient as they typically rely solely on local comparison operations and can also be readily extended (and in fact simplified) to be rotation invariant. In this paper, we provide an overview of eleven LBP-based texture algorithms and benchmark them on a set of rotated Brodatz textures.