Video summarization by a graph-theoretic FCM based algorithm

In this work, we propose a unified approach for video summarization based on the analysis of the video structure. The method originates from a data learning technique that uses the membership values produced by an over-partitioning mode of the FCM algorithm to find the connection strength between the resulting set of prototype centers. The final clustering stage is implemented by using the minimal spanning tree produced by the connectivity matrix. Based on the MST edge weights value, the clusters are derived straightforwardly and without supervision. The algorithm is finalized by the detection of video shots and the selection of key frames from each one. The method is evaluated by using objective and subjective criteria and its applicability to elongated video data set structures is very satisfactory.