Title :
A texture based method for scene change detection
Author :
T. Kar;P. Kanungo
Author_Institution :
School of Electronics Engineering, KIIT University, Bhubaneswar, India
Abstract :
Due to the growth of internet and multimedia technology, there is a tremendous need for an efficient method of automatic video retrieval and storage process. Automatic annotation is one of the key solutions for the automatic retrieval or search of a particular scene based frames or a particular scene based videos from the huge video database. Video segmentation based on shot boundary detection (Cut detection) is the fundamental step for the content based text annotation or video data analysis. In this paper, a new automatic cut detection method is proposed based on the local binary pattern feature. The proposed algorithm is tested with six test videos and its efficacy is validated with few existing popular approaches.
Keywords :
"Histograms","Feature extraction","Image edge detection","Information and communication technology","Conferences","Detection algorithms","Lighting"
Conference_Titel :
Power, Communication and Information Technology Conference (PCITC), 2015 IEEE
DOI :
10.1109/PCITC.2015.7438097