Automatic video classification using decision tree method

Abstract

Automatic digital video classification is emerging as an important problem in the fields of video analysis and multimedia database. In this paper the decision tree method is used for automatic video classification. Video clips are first segmented into shots, then features of the video clips are generated, and a video features database is created at the same time. After that, the decision tree method is used to classify the videos as different genres and a set of decision rules are produced. The discovered decision rules are used to predicate the genre of a new video. The experimental results show that the decision tree method is promising for video genre recognition.