High-Level Feature Extraction Using SIFT GMMs and Audio Models

Author

Inoue, Nakamasa ; Saito, Tatsuhiko ; Shinoda, Koichi ; Furui, Sadaoki

Author_Institution

Dept. of Comput. Sci., Tokyo Inst. of Technol., Tokyo, Japan

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

3220

Lastpage

3223

Abstract

We propose a statistical framework for high-level feature extraction that uses SIFT Gaussian mixture models (GMMs) and audio models. SIFT features were extracted from all the image frames and modeled by a GMM. In addition, we used mel-frequency cepstral coefficients and ergodic hidden Markov models to detect high-level features in audio streams. The best result obtained by using SIFT GMMs in terms of mean average precision on the TRECVID 2009 corpus was 0.150 and was improved to 0.164 by using audio information.

Keywords

Gaussian processes; audio signal processing; audio streaming; cepstral analysis; feature extraction; hidden Markov models; image processing; SIFT Gaussian mixture model; SIFT feature extraction; audio model; audio stream; ergodic hidden Markov model; high-level feature detection; high-level feature extraction; image frame; mean average precision; mel-frequency cepstral coefficient; statistical framework; Computational modeling; Data mining; Detectors; Feature extraction; Hidden Markov models; Streaming media; Visualization; HMM; MFCC; SIFT GMM;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2010 20th International Conference on

Conference_Location

Istanbul

ISSN

1051-4651

Print_ISBN

978-1-4244-7542-1

Type

conf

DOI

10.1109/ICPR.2010.787

Filename

5597163