Abstract
In outsized multimedia databases video segmentation is a fundamental constituent necessary to assist proficient content based retrieval and browsing of visual information. This paper presents work towards an integrated framework for computerized video shot detection. In this framework a set of representative key frames are selected which helps in summarizing of the entire video content into an abstract for the creation of an efficient indexing. The video frames are subdivided into its constituent variable size blocks followed by the selection of best possible similarity metric. The proposed segmentation algorithm is designed to detect any kind of shot transitions present in the video sequence. The frame structure and its color distributions are the attributes used as frame inconsistency measures. The individual key frames are selected to minimize redundancy after this segmentation step, which represent the content in each video shot thus making an abstract.