Key Frame Extraction using Edge Change Ratio for Shot Segmentation

Abstract: With an ever growing amount of video content available, digital TV, easy access to the Internet and the availability of cheap mass storage there is a huge demand for efficient indexing and content-based retrieval on large video collections. The major challenge in video processing is the amount of data that has to be processed. The huge volume of data that undergoes processing can be reduced to a large extent. This is achieved by eliminating the redundant frames of the video by using efficient key frame extraction techniques. Key frames present the most salient features of the shot eliminating any redundancy. In this paper edge change ratio algorithm is used for detecting shots of the video and key frames are extracted from these shots. The extracted key frames represent the video as a whole and can be used in variety of applications such as content based video retrieval, video summarization etc.

Keywords: key frame extraction, edge change ratio, shot segmentation.