All Issue

2014 Vol.33, Issue 6 Preview Page
Development of Audio Watermark Decoding Model Using Support Vector Machine

Support Vector Machine을 이용한 오디오 워터마크 디코딩 모델 개발

Yejin Seo1
,
Sangjin Cho1*
서 예진1
,
조 상진1*
1School of Electrical Engineering University of Ulsan
1울산대학교 전기공학부
*교신저자. *Corresponding Author. 
30 November 2014. pp. 400-406
PDF XML Citation
Abstract

This paper describes a robust watermark decoding model using a SVM(Support Vector Machine). First, the embedding process is performed inversely for a watermarked signal. And then the watermark is extracted using the proposed model. For SVM training of the proposed model, data are generated that are watermarks extracted from sounds containing watermarks by four different embedding schemes. BER(Bit Error Rate) values of the data are utilized to determine a threshold value employed to create training set. To evaluate the robustness, 14 attacks selected in StirMark, SMDI and STEP2000 benchmarking are applied. Consequently, the proposed model outperformed previous method in PSNR(Peak Signal to Noise Ratio) and BER. It is noticeable that the proposed method achieves BER 1% below in the case of PSNR greater than 10 dB.

Keywords
Audio watermarking
Support Vector Machine
Decoding model
Benchmarking

본 논문은 SVM(Support Vector Machine)을 이용하여 공격에 강인한 워터마크 디코딩 모델을 제안한다. 이 모델은 워터마크 된 신호에 대해 워터마크 삽입 과정을 역으로 수행한 후 SVM을 이용하여 워터마크를 검출한다. SVM을 생성하기 위해 먼저 4가지 워터마킹 알고리즘을 이용하여 삽입한 워터마크를 추출하여 데이터를 만들고, 이들의 BER(Bit Error Rate)을 이용하여 문턱값을 구한다. 이 후, 이 문턱값을 기준으로 훈련 집합을 만든다. 강인성 검증을 위해 워터마크 된 신호에 StirMark, SMDI, STEP2000 벤치마킹 중에서 14개의 공격을 가하였는데, 그 결과 기존의 방법보다 PSNR(Peak Signal to Noise Ratio)과 BER이 모두 개선되었다. 특히, PSNR이 10 dB 이상인 경우에는 대부분의 공격에서 1 % 이내의 BER을 갖는 우수한 성능을 보였다.

키워드
오디오 워터마킹
Support Vector Machine
디코딩 모델
벤치마킹
References
1
1.Y. G. Fu, R. Shen, and H. Lu, “Watermarking scheme based on support vector machine for color images,” Electron. Lett. 40, 986-987 (2004).
2
2.C. V. Serdean, M. Tomlinson, J. Wade, and A. M. Ambroze, “Protecting intellectual rights: digital watermarking in the wavelet domain,” in Proc. IEEE Int. Workshop Trends and Recent Achiev. in IT, 16-18 (2002).
3
3.H. J. Choi, Y. H. Seo, J. S. Yoo, and D. W. Kim, “Holomarking: digital watermarking method using fresnel hologram” (in Korean), J. Commun. Inform. Sci. Kr. 34, 604-610 (2009).
4
4.Y. Fu, R. Shen and H. Lu, “Optimal watermark detection based on support vector machines,” in Proc. Int. Symp. Neural Netw. 552-557 (2004).
5
5.M. Kutter, F. Jordan, and F. Bossen, “Digital signature of color images using amplitude modulation,” J. Electron. Imaging 7, 326-332 (1998).
6
6.C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Min. and Knowl. Discov. 2, 121- 167 (1998).
7
7.J. S. Kang and S. J. Cho, “Audio watermarking using quantization index modulation on significant peaks in frequency domain” (in Korean), J. Acoust. Soc. Kr. 30, 303-307 (2011).
8
8.Y. J. Seo, S. J. Cho, and U. P. Chong, “Watermarking algorithm using power of subbands decomposed by wavelet packet and QIM” (in Korean), J. Multimed. Soc. Kr. 14, 1431-1437 (2011).
9
9.Y. J. Seo, S. J. Cho, and U. P. Chong, “Multiple audio watermarking using quantization index modulation on frequency phase and magnitude response” (in Korean), J. Acoust. Soc. Kr. 32, 71-78 (2013).
10
10.K. P. Shine, and S. Krishna Kumar, “Extended bipolar echo kernel for audio watermarking,” in Proc. ARTCom, 487-489 (2009).
11
11.I. Y. An., “Adaptive watermarking method using watermark detection rate” (in Korean), J. Inst. Electron. Commun .Sci. Kr. 5, 465-470 (2010).
12
12.A. Lang, Stirmark benchmark for audio, http://wwwiti.cs.uni- magdeburg.de/~alang/smba.php, 2007.
13
13.Y. Lin and W. H. Abdulla, “Audio watermarking for copyright protection,” University of Auckland, Auckland, New Zealand, Tech. Rep., 2007.
14
14.JASRAC and NRI Ltd., “Announcement of Evaluation Test Results for ‘STEP 2000’, International Evaluation Project for Digital Watermark Technology for Music,” http://www. jasrac.or.jp/watermark/ehoukoku.htm, 2000.
Information
  • Publisher :The Acoustical Society of Korea
  • Publisher(Ko) :한국음향학회
  • Journal Title :The Journal of the Acoustical Society of Korea
  • Journal Title(Ko) :한국음향학회지
  • Volume : 33
  • No :6
  • Pages :400-406
  • Received Date : 2014-06-18
  • Revised Date : 2014-09-11
  • Accepted Date : 2014-09-26
  • DOI :https://doi.org/10.7776/ASK.2014.33.6.400
Journal Informaiton The Journal of the Acoustical Society of Korea The Journal of the Acoustical Society of Korea
E-Book
  • scopus_JASK
  • ESCI_JASK
  • Google scholar_JASK
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • ccl
Journal Informaiton Journal Informaiton - close