RELEVANCE FEEDBACK METHODS IN CONTENT BASED RETRIEVAL AND VIDEO SUMMARIZATION (ThuPmOR2)

Author(s) : Micha Haas (LIACS Media Lab, Netherlands) Michael Lew (LIACS Media Lab, Netherlands) Ard Oerlemans (LIACS Media Lab, Netherlands)

Abstract : In the current state-of-the-art in multimedia content analysis (MCA), the fundamental techniques are typically derived from core pattern recognition and computer vision algorithms. It is well known that completely automatic pattern recognition and computer vision approaches have not been successful in being robust and domain independent so we should not expect more from MCA algorithms. The exception to this would naturally be methods which are not automatic or human-interactive methods. In this paper, we describe some of the recent work we have done in multimedia content analysis across multiple domains where the fundamental technique is founded in relevance feedback. Our algorithm integrates work from wavelet based salient points and genetic algorithms and shows that the fundamental improvement is from the user feedback.

Menu