Identification and Elimination of Similar Images in an Event Image Set

Over the past decade Video and Image data is accumulated in the storage media of various commercial organizations, government and educational Institutions. Events are organized round the year in these organizations and are recorded through the digital devices installed at the event venues. Eventually the data is piled up in the electronic vaults and the end-users are unaware of the implications and importance of this data. Thus an automated system is needed for the image data to be indexed, captioned and maintained as an archive to extend quick summary of events for preparing annual documents, magazines and departmental newsletters. This paper focus on preprocessing of the captured image data to identify and eliminate similar images. The resulting image set thus eliminate redundant data and in turn reduce the storage space.