A novel shot boundary detection based on information theory using SVM
Jialei Bi, Xianglong Liu, Bo Lang · 2011
Shot boundary detection is the preliminary step for efficient video indexing and retrieval. To overcome the shortage of traditional threshold based method in shot detection, we proposed a novel cut detection method based on information theory using SVM. We first compute the dissimilarity using information theory and construct a discriminative feature vector based on mutual information. Then a support vector machine is trained to classify the frames as cut or none-cut frames. Experiment results demonstrate our proposed method is effective and outperforms state-of-art methods.