An Approach of Commercials Detection Based on Audio-match

doi:10.3969/j.issn.1006-2475.2014.02.001

Abstract

Abstract: Commercials detection is to extract advertising sequence out of TV shows automatically. In traditional ways, it adopted algorithm based on computer vision technology framework to detect advertisement in terms of video content. But it wouldn’t meet the demands on performance or efficiency for commercial usage. The algorithm described here used only audio information for detection. It first extracted original audio information from video, then used short-time Fourier transform to transform it into a spectrogram. And it applied binary threshold with a set of pre-boosting filters to get local feature descriptors. During the detect phase, it obtained descriptors in the same methods described above, and detected results in offline descriptor library. Audio-based detection algorithm for commercials detection had smaller storage, higher accuracy, and better real-time. Experiments showed that this algorithm could significantly improve robustness and performance of commercials detection systems, and can be applied in reality.

Key words: commercials detection, audio-match, spectrogram, Haar-like feature, feature descriptor, bounding point, smooth

CLC Number:

TP391

ZHAO Hua-ting1, WANG Ming-min1,2 . An Approach of Commercials Detection Based on Audio-match[J]. Computer and Modernization, 2014, 0(2): 1-5.

References

[1] Lienhart R, Kuhmunch C, Effelsberg W. On the detection and recognition of television commercials[C]// Proceedings of the 1997 IEEE International Conference on Multimedia Computing and Systems. Ottawa, Canada, 1997:509-516.

[2] Ke Y, Sukthankar R, Huston L. Efficient near-duplicate detection and sub-image retrieval[C]// Proceedings of the 2004 ACM International Conference on Multimedia. New York, USA, 2004:869-876.

[3] Sadlier D A, Marlov S, O’Connor N E, et al. Automatic TV advertisement detection from MPEG bitstream[C]// Proceedings of the 1st International Workshop on Pattern Recognition in Information Systems. Setubal, Portugal, 2001:14-25.

[4] Hua X S, Lu L, Zhang H J. Robust learning-based TV commercial detection[C]// Proceedings of the 2005 IEEE International Conference on Multimedia and Expo. 2005:149-152.

[5] 丁汝一,杨宁,董道国. 音视频相结合的广告检测算法[J]. 计算机工程与应用, 2012,48(22):184-188.

[6] Ke Y, Hoiem D, Sukthankar R. Computer vision for music identification[C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005:597-604.

[7] Jurado F, Saenz J R. Comparison between discrete STFT and wavelets for the analysis of power quality events[J]. Electric Power Systems Research, 2002,62(3):183-190.

[8] Jones M, Viola P. Face Recognition Using Boosted Local Features[R]. Technical Report MERL-TR-2003-25, Mitsubishi Electric Research Laboratories, 2003.

[9] Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001,1:511-518.

[10] Schapire R E, Singer Y. Improved boosting algorithms using confidence-rated predictions[J]. Machine Learning, 1999,37(3):297-336.

[11] Indyk P, Motwani R. Approximate nearest neighbors: Towards removing the curse of dimensionality[C]// Proceedings of the 30th Annual ACM Symposium on Theory of Computing. 1998:604-613.

[12] Gionis A, Indyk P, Motwani R. Similarity search in high dimensions via hashing[C]// Proceedings of the 25th International Conference on Very Large Data Bases. 1999:518-529.

[13] Bhattacharryya D K, Nandi S. An efficient class of SEC-DED-AUED codes[C]// Proceedings of the 1997 International Symposium on Parallel Architectures, Algorithms and Networks. 1997:410-416.

[14] Lowe D G. Object recognition from local scale-invariant features[C]// Proceedings of the 7th IEEE International Conference on Computer Vision. 1999,2:1150-1157.

[15] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981,24(6):381-395.

[16] McLachlan G, Krishnan T. The EM Algorithm and Extensions[M]. Wiley-Interscience, 1997.

[17] Duan L Y, Wang J, Zheng Y, et al. Segmentation, categorization, and identification of commercials from TV streams using multimodal analysis[C]// Proceedings of the 14th Annual ACM International Conference on Multimedia. 2006:201-210.