Hierarchical vs non-hierarchical audio indexation and classification for video genres

Nouha Dammak; Yassine BenAyed

doi:10.1117/12.2309852

Translator Disclaimer

13 April 2018 Hierarchical vs non-hierarchical audio indexation and classification for video genres

Nouha Dammak; Yassine BenAyed

Author Affiliations +

Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 1069621 (2018) https://doi.org/10.1117/12.2309852
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria

Abstract

In this paper, Support Vector Machines (SVMs) are used for segmenting and indexing video genres based on only audio features extracted at block level, which has a prominent asset by capturing local temporal information. The main contribution of our study is to show the wide effect on the classification accuracies while using an hierarchical categorization structure based on Mel Frequency Cepstral Coefficients (MFCC) audio descriptor. In fact, the classification consists in three common video genres: sports videos, music clips and news scenes. The sub-classification may divide each genre into several multi-speaker and multi-dialect sub-genres. The validation of this approach was carried out on over 360 minutes of video span yielding a classification accuracy of over 99%.

Citation Download Citation

Nouha Dammak and Yassine BenAyed "Hierarchical vs non-hierarchical audio indexation and classification for video genres", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 1069621 (13 April 2018); https://doi.org/10.1117/12.2309852

PROCEEDINGS
8 PAGES

DOWNLOAD PDF SAVE TO MY LIBRARY

SHARE

GET CITATION

< Previous Article

|

Next Article >

KEYWORDS

Video

Feature extraction

Databases

Visualization

Information visualization

Fourier transforms

Classification systems

RELATED CONTENT

Saliency detection for videos using 3D FFT local spectra
Proceedings of SPIE (March 17 2015)

Fusion of visual and audio features for person identification in...
Proceedings of SPIE (January 01 2001)

Similarity indexing: algorithms and performance
Proceedings of SPIE (March 13 1996)

Video classification using speaker identification
Proceedings of SPIE (January 15 1997)

Model-based classification of visual information for content-based retrieval
Proceedings of SPIE (December 17 1998)

Measurement of tag confidence in user generated contents retrieval
Proceedings of SPIE (January 19 2009)

Semantically controlled content-based retrieval of video sequences
Proceedings of SPIE (October 05 1998)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years