A Novel Hybrid System based on Fractal Coding for Soccer Retrieval from Video Database

Most information retrieval systems make indirect use of human knowledge in their retrieval process. The novel systems presented here uses the human knowledge directly to retrieve the soccer events. The proposed system is an extended method in three aspects as follows: in the query model, the query by example and query by keywords are applied to retrieve the semantics. In feature extraction, we propose novel methods for extracting the caption as important cinematic feature and for detecting the player gathering. And in the retrieval process, a novel method based on fractal coding is proposed here. The first phase consists of extracting suitable features and key frames from video shots. Then, using a fractal coding, soccer shots are retrieved, and using a fuzzy rule base system, shots that do not include significant soccer events are removed. Experimental results show high accuracy of proposed caption extraction and player gathering detection algorithm and satisfying retrieval process.