Semantically Controlled Content-Based Retrieval of Video Sequences

In this paper, we present a technique for automatic classification of movies based on their content. This technique analyses shot duration and motion energy of movie trailers to characterize them as Action/Character movies. This approach is then combined with a features-based technique for content-based retrieval of video. Experiments indicate a high retrieval accuracy (greater than 96%) together with semantic-control (Action vs. Character) with this combined approach. Keywords: Content-based retrieval, density estimation, Kullback-Liebler divergence 1. INTRODUCTION Digital imagery is becoming increasingly important in day-to-day communications. However, the technology for organizing and searching imagery is still a subject of intensive research. Currently, a common approach to searching image and video data is to create textual annotations by hand. However, such a textual annotation is highly dependent on the human operator. Even if we could counter that, the multitude of spatial re..