Video summarization by clustering using euclidean distance

Recent advances in technology have made tremendous amount of multimedia information available to the general population. A practical way of dealing with this new scenario is to develop browsing tools that distil multimedia data as information oriented summaries. Such an approach will not only suit resource poor environments such as wireless and mobile, but also enhance browsing on the wired side for applications like digital libraries and repositories. Summarization techniques will give choice to users to browse and select the multimedia documents of their need for complete viewing later. In this work, we are proposing a summarization technique to gather the frames of interest in a video. The method is based on the removal of redundant frames in a video and the maintenance of user defined number of unique frames. It works on the process of clustering, where visually similar frames are clustered into one group using the Euclidean distance measure. When clusters are formed, a fraction of the frames that has given a larger distance metric is retrieved from each group to form a sequence making up the desired output. This method ensures that video summary represents the most unique frames of the input video and gives equal attention to preserving continuity of the summarized video.