Image hashing by CCQ-CSLBP

Abstract

Recent trends and also statistics show that the hashing concept has been gaining importance because its application lies in the area of authentication, retrieval and recognition. The proposed hashing method CCQ-CSLBP (Compressed CSLBP with Correlation Coefficient) for authentication utilized correlation coefficient as a weight factor in CSLBP. CSLBP is a texture operator, whose performance is better than LBP, in terms of rotation invariance, differentiation power and less number of histogram bin. In CSLBP, histogram of each sub block is represented by 16 bin. Reduction in number of histogram bin is achieved by the flipped difference concept. Proposed method takes the advantage of correlation coefficient as a boosting factor during histogram construction, to increase the discrimination power of compressed CSLBP. With the use of correlation coefficient, results of CSLBP improved, in terms TPR and FPR. CCQ-CSLBP is evaluated, based on normalized hamming distance and ROC characteristics.