A novel video summarization algorithm

Abstract

This paper presents a new genetic algorithm based method for video summarization. We pick out the least similar images from original video by measuring the differences with the technique of color histograms. Based on this reduced set, fitness function is defined for genetic algorithm to search the optimized frames. Experimental results show that the proposed method can capture more information than the traditional method and avoid redundancy. Moreover this algorithm has a distinct advantage in terms of time.