Cartoon-recognition using video & audio descriptors

We present a new approach for classifying mpeg-2 video sequences as `cartoon´ or `non-cartoon´ by analyzing specific video and audio features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres like cartoon, commercial, music, news and sports are studied. Such applications have also been discussed in the context of MPEG-7 [12]. In our method the extracted features from the visual descriptors are non-linearly combined using a multilayered perceptron and then considered together with the output of the audio-descriptor to produce a reliable recognition. The results demonstrate a high identification rate based on a large collection of 100 representative video sequences (20 cartoons and 4*20 non-cartoons) gathered from free digital TV-broadcasting.