An Automated Video Classification and Annotation Using Embedded Audio for Content Based Retrieval

Efficient and effective video classification and annotation demands automated unsupervised classification and annotation of videos based on its embedded video content as manual indexing is unfeasible. Audio is a rich source of information in the digital videos that can provide useful descriptor for indexing the video databases. Audio archives contrast with image or video archives in a number of important dimensions. First, they capture information from all directions and are largely robust to sensor position and orientation, allowing data collection without encumbering the user. Second, the nature of audio is distinct from video, making certain kinds of information (for example, what is said) more accessible, and other information (for example, the presence of nonspeaking individuals) unavailable. In general, processing the content of an audio archive could provide a wide range of useful information. As a first step the audio content of video is extracted and cleaned for further processing the next step converts audio into textual format .The text is processed upon to get the prime keywords in the video using text mining. The videos are classified and annotated on the keywords thus found. The annotated videos 