The Face Recognition Algorithm Based on Double Coding Local Binary Pattern

摘要

This paper proposes a new Double Coding Local Binary Pattern algorithm (d-LBP) to improve the weaknesses of traditional LBP algorithm. Firstly, it defines two thresholds: the amplitude threshold and the difference threshold, which succeed in taking full consideration of the relationship among pixel gray values and reducing sampling points. Secondly, the paper uses the d-LBP algorithm to extract statistical characteristics from each small block of the original face image. Finally, it ful fills the face recognition by using K Nearest Neighbor algorithm.