|Proc. of the 7th International Conference on Advanced Communication Technology (ICACT)
|1121 - 1124
|Ronald Glasberg, Khalid Elazouzi, Thomas Sikora
|Video-genre-classification: recognizing cartoons in real-time using visual-descriptors and a multilayer-percetpron
|We present a new approach for classifying MPEG-2 video sequences as ‘cartoon’ or ‘non-cartoon’ by analyzing pecific color, texture and motion features of consecutive frames in real-time. This is part of the well-known ideo-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. In our method the extracted features from the visual descriptors are nonlinear weighted with a sigmoid-function and afterwards combined using a multilayered perceptron 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.