Shot boundary detection using color correlogram and Gauge-SURF descriptors

Automatic shot boundary detection has been identified to be one of the important and challenging research areas. Shot boundary detection is mainly helpful in video summarization, video indexing and content based video retrieval systems. In this paper we propose an efficient algorithm to detect shot boundaries using color correlogram and Gauge-Speeded-up robust features. Proposed algorithm analyses the changes in color correlogram and the correspondence between Gauge-Speeded-up robust features over selected frames of a video to find the shot boundaries. Our proposed methodology can detect both abrupt and gradual shot boundaries in videos efficiently. Experimental results clearly prove the effectiveness of our proposed method in detecting shot boundaries.