Image splicing detection using 2-D phase congruency and statistical moments of characteristic function

摘要: A new approach to efficient blind image splicing detection is proposed in this paper. Image the process of making a composite picture by cutting and joining two or more photographs. The spliced may introduce number of sharp transitions such as lines, edges corners. Phase congruency has been known sensitive measure of these sharp hence features for detection. In addition phase information, the magnitude information also used Specifically, statistical moments characteristic functions of wavelet subbands have examined catch difference between authentic images images. Consequently, scheme extracts from wavelet 2-D phase experiments demonstrated that can achieve higher rate compared with state-of-the-art.