The Face Recognition Algorithm Based On Double Coding Local Binary Pattern

This paper proposes a new Double Coding Local Binary Pattern algorithm (d-LBP) to improve the weakness of traditional LBP algorithm, such as, incompletely features extraction, too much sample points, low computational efficiency and so forth. 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 in each small block of the original face image. Finally, it fulfills the face recognition by using K Nearest Neighbor algorithm.