In this work, the idea of key frames extraction methods based on graph theory [7] and curve splitting [8], [9] from single shots in video sequences is presented. The method is have also been presented.implemented by an efficient two-step algorithm, which isThe idea pursued in this work is applicable to cases where classified neither to clustering nor to temporal variations based the frames of a video do not show any cluster organization.techniques. In the first step, an MST (minimal spanning tree) This is a common situation, met in several video shots; video graph is constructed, where each node is associated to a single showing a speaker being a characteristic example. The feature frame of the shot. In the second step, extracts key frames based extracted for each frame representation is the HSV color on the principle of their maximum spread, are extracted. The histogram and our work is based on direct manipulation of the number of the selected key frames is controlled by an adaptively dissimilarity matrix of the feature vectors of the frames. The defined threshold, while the validity of the results is evaluated by content correlation of the frames is re-estimated according to the fidelity measure.the MST graph analysis [10] and an appropriate algorithm
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.