Title :
Video similarity measurement using spectrogram
Author :
Khoenkaw, P. ; Piamsa-nga, P.
Author_Institution :
Dept. of Comput. Eng., Kasetsart Univ., Bangkok, Thailand
fDate :
July 30 2014-Aug. 1 2014
Abstract :
A new video similarity measurement method is developed for video copy detection. The ordinal feature is transformed to spectrogram by Short-Time Fourier Transform to represent as a video signature. Similarity between video signatures was measured by using DTW algorithm. The experiments on the CC_WEB_VIDEO dataset show that accuracy of this algorithm is 19.6%, 11.7%, and 16.6% as high as Sliding Window, DTW and STD methods, respectively in both “minor edited” and “extensively edited” video categories.
Keywords :
Fourier transforms; feature extraction; image matching; time warp simulation; video signal processing; CC_WEB_VIDEO dataset; DTW algorithm; DTW method; STD method; dynamic time warping; ordinal feature extraction; short-time fourier transform; sliding window; spectrogram; video copy detection; video matching; video signature; video similarity measurement; Algorithm design and analysis; Computer science; Dynamic programming; Feature extraction; Heuristic algorithms; Spectrogram; Vectors; dynamic time warping; near-duplicate; redundancy detection; similarity measure; spectrogram; video database; video matching; video search; web video;
Conference_Titel :
Computer Science and Engineering Conference (ICSEC), 2014 International
Conference_Location :
Khon Kaen
Print_ISBN :
978-1-4799-4965-6
DOI :
10.1109/ICSEC.2014.6978241