Due to the recent development in the technology, large amount of video data is being produced nowadays. If any user needs to search for a video related to a particular topic, then he is unnecessarily bound to look into many videos fully to get the relevant content. Video summarization provides a concise representation of the content of a video while preserving the essential information. Many methods for summarization have been proposed so far, but most of them are time consuming and require large amount of computational space. In this paper, we present a new DCT-based static video summarization, which utilizes the DCT information of each frame. This method effectively measures the correlation between the successive frames and then selects frames having content different from their respective neighboring frames. Our results of summarization are found to be 90% closer to the user summary
Video summarization, Discrete Cosine Transformation, Pearson Correlation Coefficient, F-measure, Key Frames.
Prachi Singh; Suneeta Agarwal, DCT-Based Static Video Summarization, HCTL Open International Journal of Technology Innovations and Research (IJTIR), Volume 14, April 2015, eISSN: 2321-1814, ISBN (Print): 978-1-62951-946-3.