Dual Tree Discrete Wavelet Transform and Entropy based Approach for Video Shot Boundary Detection

Abstract

Shot Boundary detection is one of the most prominent steps for the various video processing techniques like indexing of videos, video retrieval, video summarization, video scene analysis, etc. In this paper, we have projected a useful technique based on dual-tree Discrete Wavelet Transform. The dual-tree structure with selected filters returns the approximate decomposition in an analytical manner. Due to the existence of the two trees, the noise component is characterized precisely. The outcome of the DTDWT is distortion less with normalized localized function and exact reconstruction of the signal. WE have used the entropy function to measure the uncertainty in the random variable. Finally, we evaluated the algorithm using Recall, Precision, and F1 measure. Experimental results demonstrate the efficiency of the given method.