Title :
Audio-video based segmentation and classification using SVM
Author :
Subashini, K. ; Palanivel, S. ; Ramaligam, V.
Author_Institution :
Annamalai Univ., Chidambaram, India
Abstract :
In this paper, we propose a method for combining audio and video for segmentation and classification. The objective of segmentation is to detect category change point such as news followed by advertisement. The classification system classify the audio and video data into one of the predefined categories such as news, advertisement, sports, serial and movies. Automatic audio-video classification is very useful to audio-video indexing, content based audio-video retrieval. Mel frequency cepstral coefficients is used as acoustic features and color histogram is used as visual features for segmentation and classification. Support vector machine (SVM) is used for both segmentation and classification. The experiments on different genres illustrate the results of classification are significant. Experimental results of audio classification evidence and video are combined using weighted sum rule for audio-video based segmentation and classification.
Keywords :
content-based retrieval; image classification; image colour analysis; image segmentation; multimedia systems; support vector machines; video retrieval; SVM; acoustic feature; audio-video based segmentation; audio-video classification; audio-video indexing; color histogram; content based audio-video retrieval; mel frequency cepstral coefficient; support vector machine; visual feature; weighted sum rule; Hidden Markov models; Image segmentation; Motion pictures; RNA; Support vector machines; Audio classification; Audio-video classification; Color histogram; Mel frequency cepstral coefficients; Support vector machines; Video classification;
Conference_Titel :
Computing Communication & Networking Technologies (ICCCNT), 2012 Third International Conference on
Conference_Location :
Coimbatore
DOI :
10.1109/ICCCNT.2012.6395919
