Performance Study of Soft Local Binary Pattern over Local Binary Pattern under Noisy Images

Abstract

In this paper, the performance of soft local binary pattern (SLBP) method has been investigated with edge detection techniques for face recognition in case of noisy condition. Various edge detection techniques such as Canny, Robert and Log methods have been used with SLBP for recognizing faces. The results obtained using SLBP with various edge detection for noisy condition based on image quality measurement shows better recognition rate compared to the results obtained using local binary pattern (LBP). Simplified edge detection methods simplify the images as a result SLBP with edge detection requires less computation time compared with edge detection of LBP.