Video similarity measurement using spectrogram

Author

Khoenkaw, P. ; Piamsa-nga, P.

Author_Institution

Dept. of Comput. Eng., Kasetsart Univ., Bangkok, Thailand

fYear

2014

fDate

July 30 2014-Aug. 1 2014

Firstpage

463

Lastpage

468

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Engineering Conference (ICSEC), 2014 International

Conference_Location

Khon Kaen

Print_ISBN

978-1-4799-4965-6

Type

conf

DOI

10.1109/ICSEC.2014.6978241

Filename

6978241