Automatic Genre Identification for Content-Based Video Categorization

13 years 9 months ago

Download www.computing.edu.au

Thispaper presents a set of computationalfeatures originatingfrom our study of editing effects, motion, and color used in videos,for the task of automatic video categorization. These features besides representing human understanding of typical attributes of different video genres, are also inspired by the techniques and rules used by many directors toendowspecific characteristicstoa genre-program which lead to certain emotional impact on viewers. Wepropose new features whilst also employing traditionallyused onesfor classification. This research, goes beyond the existing work with a systematic analysis of trends exhibited by each of our features in genres such as cartoons, commercials, music, news, and sports, and it enables an understanding of the similarities, dissimilarities, and also likely confusion between genres. ClassiJicationresultsfrom our experiments on several hours of video establish the usefulness of thisfeature set. We also explore the issue of video clip duration requi...

Ba Tu Truong, Svetha Venkatesh, Chitra Dorai

Real-time Traffic