Neural-fuzzy approach for content-based retrieval of digital video

As digital video databases become more and more pervasive, finding video in large databases becomes a major problem. Because of the nature of video (streamed objects), accessing the content of such databases is inherently a time-consuming operation. The paper proposes a novel neural-fuzzy based approach for retrieving a specific video clip from a video database. Fuzzy logic is used for expressing queries in terms of natural language and a neural network is designed to learn the meaning of these queries. The queries are designed based on features such as colour and texture of shots, scenes and objects in video clips. An error backpropagation algorithm is proposed to learn the meaning of queries in fuzzy terms such as "very similar", "similar" and "some-what similar". Preliminary experiments were conducted on a small video database and different combinations of queries using colour and texture features along with a visual video clip; very promising results were achieved.