Paper Title
Video Summarization using unsupervised learning using Color Histogram

Abstract
In last several years machine learning approaches have gained popularity, we proposed framework for video summarization using unsupervised learning. According to proposed method multiple features, obtained from video frames, are combined to describe the frame difference between consecutive frames. It is observed that certain frame difference features have more influence in generating a representative frame difference measure. Moreover, some features are more relevant than others in different video genres. We used three different low level features color histogram, correlation and edge orientation histogram and generate feature vector. Fuzzy c-means and k-means have been effectively used to generate meaningful, enjoyable video summary using generated feature vector. We have conducted large no. of experiments to show effectiveness and robustness of the approach. Generated results reflect that fuzzy c-means succeeds to preserve better informative summary than K-means.