Fast Film Genres Classification Combining Poster and Synopsis

In this paper, we present an efficient approach to fast classify film genre by making use of film posters and synopsis simultaneously. Compared with traditional video content-based classification methods, the proposed method is much faster and more accurate. In the proposed method, a film poster is represented as multiple features including color, edge, texture, and the number of faces. On the other hand, we employ Vector Space Model (VSM) to characterize the texts in the synopsis. Then, we train a poster classifier and a text classifier using the Support Vector Machine (SVM). Finally, a test film is classified based on the 'OR' operation on the outputs of the two classifiers. We verify our scheme on our collected film poster and synopsis dataset. The experimental results demonstrate the promise of our method which achieves the desirable performance by combining posters with synopsis.