The objective in any pattern recognition problem is to capture the characteristics common to each class from features of the segmented data. Audio-video segmentation and classification can provide useful information for multimedia indexing and retrieval. In this study, researchers present a approach to segment and categorize the audio-video classification and highlighted detection. Researchers investigate the performance of Mel-frequency cepstral coefficients and color histogram in a support vector machines frame work and compare it to traditional audio-video features. Researchers achieve a correct identification closed to 96.23% on proposed method. Thus, the new technology for audio-video segmentation and classification obtained effective and efficient results compared to individual results.
展开▼
