Semantic Categorization of Video: An Evolutionary Learning based Approach

Abstract

In this paper, we have proposed a fuzzy rule based system for classification of video into semantic categories. The classification scheme uses an evolutionary learning methodology to evolve a fuzzy system for use in the classification process. This evolved fuzzy classifier has the inherent capability to tackle variations and ambiguities invariably present in the video data. A novel fuzzy theoretic sheme has been suggested for extraction of key frames from a given video after shot segmentation. Frame based temporal features and spatial features obtained from key frames have been used in the classification system. We have developed an experimental system for categorization of sports video. The experimental system has yielded reasonably correct recognition results for a large number of samples.

Indexing terms:

• Evolutionary Learning based
• Semantic categorisation
• Fuzzy rule based systems (FRBS)
• Key frame based extraction
• Scene dynamics based classification

Additional information

Notes on contributors

R S Jadon

RS Jadon obtained his MCA degree from MITS Gwalior in 1989. He joined the Department of Computer Application, MITS Gwalior as a member of faculty in 1989. He is currently Reader in the same Department. He is pursuing his PhD degree in the area of Video Data Processing at the Department of Computer Science and Engg., IIT Delhi. His research interests are computer vision, image processing, video segmentation and classification. He is life member of IETE, CSI and ISTE India.

K K Biswas

K K Biswas graduated in Electrical Engg from IIT Madras in 1968. After completing his MTech and PhD in 1974 from IIT Delhi, he joined as faculty member in Electrical Engg, Department of IIT Delhi. He shifted to Computer Science and Engg. Department in 1984 where he is currently a Professor. His current interests are in the area of video compression, video segmentation and characterization, visualization and medical imaging. He is on the editorial board of Journal of Networks and Applications and PAA. He is coordinator of Indo-US collaborative project on Integrated Synthetic Environments with University of Texas at Austin.

Asma Shakil

Asma Shakil has completed her MTech degree in Computer Technology from IIT Delhi in December 2000. In her MTech Project she has implemented the schemes for Evolutionary learning using genetic algorithms.