Abstract: This study presents a method to classify audio-video data into one of seven classes: advertisement, cartoon, news, movie and songs. Automatic audio-video classification is very useful to audio-video indexing, content based audio-video retrieval. Mel frequency cepstral coefficients are used to characterize the audio data. The color histogram features extracted from the images in the video clips are used as visual features. Support vector machine is used for audio and video segmentation and classification. The experiments on different genres illustrate the results of segmentation and classifications are significant and effective. Experimental results of audio classification and video segmentation and classification results are combined using weighted sum rule for audio-video based classification. The method classifies the audio-video clips with an accuracy of 95.79%.
K. Subashin, S. Palanivel and V. Ramaligam, 2012. Audio_Video Based Segmentation and Classification Using SVM. Asian Journal of Information Technology, 11: 30-35.