LBP Feature Combination Strategies and Their Application on Face Recognition

Download Now Date Added: Feb 2012
Format: PDF

Local Binary Patterns (LBP) is a simple but efficient feature descriptor for texture analysis. In this paper, the authors discuss LBP feature combination strategies, including three block strategies, single-blocked, multi-blocked and sliding windows. The experimental results on face recognition tasks show that the combination strategies can extract the texture features very well. Feature extraction is a fundamental and challenging task in computer vision field and pattern recognition applications. Local Binary Patterns (LBP) was first proposed by Ojala et al. to encode the pixel-wise information in the texture images.