대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

Gabor 특징과 웨이브렛 영역의 BDIP와 BVLC 특징을 이용한 질감 특징 기반 언어 인식

Texture Feature-Based Language Identification Using Gabor Feature and Wavelet-Domain BDIP and BVLC Features

  • 장익훈 (경운대학교 디지털전자공학과) ;
  • 이우신 (경북대학교 전자공학부) ;
  • 김남철 (경북대학교 전자공학부)
  • Jang, Ick-Hoon (Department of Digital Electronic Engineering, Kyungwoon University) ;
  • Lee, Woo-Shin (School of Electronics Engineering, Kyungpook National University) ;
  • Kim, Nam-Chul (School of Electronics Engineering, Kyungpook National University)
  • 투고 : 2010.11.06
  • 심사 : 2011.05.04
  • 발행 : 2011.07.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 Gabor 특징과 웨이브렛 영역의 BDIP와 BVLC 특징을 이용한 질감 특징 기반 언어 인식 방법을 제안한다. 제안된 방법에서는 먼저 시험 영상에 Gabor 변환과 웨이브렛 변환을 적용한다. 웨이브렛 영역의 상세 대역에는 Donoho의 연역치화를 적용하여 잡음을 제거한다. 이어서 Gabor 영상에는 크기 연산자를 적용하고 웨이브렛 부대역에는 BDIP와 BVLC 연산자를 적용한다. 그런 다음 Gabor 크기 영상과 BDIP, BVLC 부대역에 대하여 통계치를 계산하여 그 결과들을 벡터화하고 융합하여 특징 벡터로 사용한다. 분류 단계에서는 얼굴 인식에 주로 사용되는 WPCA를 분류기로 하여 시험 특징 벡터와 가장 유사한 학습 특징 벡터를 찾는다. 실험 결과 제안된 방법은 실험 문서 영상 DB에 대하여 비교적 낮은 특징 벡터 차원으로 매우 우수한 언어 인식 성능을 보여준다.

In this paper, we propose a texture feature-based language identification using Gabor feature and wavelet-domain BDIP (block difference of inverse probabilities) and BVLC (block variance of local correlation coefficients) features. In the proposed method, Gabor and wavelet transforms are first applied to a test image. The wavelet subbands are next denoised by Donoho's soft-thresholding. The magnitude operator is then applied to the Gabor image and the BDIP and BVLC operators to the wavelet subbands. Moments for Gabor magnitude image and each subband of BDIP and BVLC are computed and fused into a feature vector. In classification, the WPCA (whitened principal component analysis) classifier, which is usually adopted in the face identification, searches the training feature vector most similar to the test feature vector. Experimental results show that the proposed method yields excellent language identification with rather low feature dimension for a document image DB.

키워드

참고문헌

  1. D. Ghosh, T. Dube, and A. P. Shivaprasad, "Script recognition - a review," IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, Jan. 2010.
  2. J. Hochberg, L. Kerns, P. Kelly, and T. Thomas, "Automatic script identification from document images using cluster-based templates," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 2, pp. 176-181, Feb. 1997. https://doi.org/10.1109/34.574802
  3. A. L. Spitz, "Determination of the script and language content of document images," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 3, pp. 235-245, Mar. 1997. https://doi.org/10.1109/34.584100
  4. L. Shijian and C. L. Tan, "Script and language identification in noisy and degraded document images," IEEE Trans. Pattern Anal. Mach. Intell., vol. 30, no. 1, pp. 14-24, Jan. 2008. https://doi.org/10.1109/TPAMI.2007.1158
  5. G. S. Pearke and T. N. Tan, "Script and language identification from document images," in Proc. IEEE Workshop on Document Image Analysis 97, San Juan, Puerto Rico, Jun. 1997, pp. 10-17.
  6. T. N. Tan, "Rotation invariant texture features and their use in automatic script identification," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 7, pp. 743-756, Jul. 1998.
  7. W. Chan and G. Coghill, "Text analysis using local energy," Pattern Recognit., vol. 34, no. 12, pp. 2523-2532, Dec. 2001. https://doi.org/10.1016/S0031-3203(00)00155-2
  8. A. Busch, W. W. Boles, and S. Sridharan, "Texture for script identification," IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 11, pp. 1720-1732, Nov. 2005. https://doi.org/10.1109/TPAMI.2005.227
  9. W. S. Lee, N. C. Kim, and I. H. Jang, "Texture feature-based language identification using wavelet-domain BDIP, BVLC, and NRMA features," in Proc. IEEE International Workshop on Machine Learning for Signal Processing 2010, Kittilä, Finland, Aug./Sep. 2010, pp. 444-449.
  10. R. M. Haralick, K. Shanmugam, and I. Dinstein, "Textural features for image classification," IEEE Trans. Syst., Man, Cybern., vol. SMC-3, no. 6, pp. 610-621, Nov. 1973. https://doi.org/10.1109/TSMC.1973.4309314
  11. Y. D. Chun, S. Y. Seo, and N. C. Kim, "Image retrieval using BDIP and BVLC moments," IEEE Trans. Circuits Syst. Video Technol., vol. 13, no. 9, pp. 951-957, Sep. 2003. https://doi.org/10.1109/TCSVT.2003.816507
  12. Y. D. Chun, N. C. Kim, I. H. Jang, "Content-based image retrieval using multiresolution color and texture features," IEEE Trans. Multimedia, vol. 10, no. 6, pp. 1073-1084, Oct. 2008. https://doi.org/10.1109/TMM.2008.2001357
  13. B. S. Manjunath and W. Y. Ma, "Texture features for browsing and retrieval of image data," IEEE Trans. Pattern Anal. Mach. Intell., vol. 18, no. 8, pp. 837-842, Aug. 1996. https://doi.org/10.1109/34.531803
  14. H. J. So, M. H. Kim, and N. C. Kim, "Texture classification using wavelet-domain BDIP and BVLC features," in Proc. 17th European Signal Processing Conf., Glasgow, Scotland, Aug. 2009, pp. 1117-1120.
  15. H. J. So, M. H. Kim, Y. S. Chung, and N. C. Kim, "Face detection using sketch operators and vertical symmetry," FAQS-2006, Lecture Notes in Artificial Intelligence, vol. 4027, pp. 541-551, Jun. 2006.
  16. Y. A. Ju, H. J. So, N. C. Kim, and M. H. Kim, "Face recognition using local statistics of gradients and correlations," in Proc. 18th European Signal Processing Conf., Aalborg, Denmark, Aug. 2010, pp. 1169-1173.
  17. T. D. Nguyen, S. H. Kim, and N. C. Kim, "An automatic body ROI determination for 3D visualization of a fetal ultrasound volume," KES-2005, Lecture Notes in Artificial Intelligence, vol. 3682, pp. 145-153, Sep. 2005.
  18. D. L. Donoho, "De-noising by softthresholding," IEEE Trans. Inform. Theory, vol. 41, no. 3, pp. 613-627, May 1995. https://doi.org/10.1109/18.382009
  19. Q. A. Holmes, D. R. Neusch, and R. A. Shuchman, "Textual features for image classification," IEEE Trans. Geosci. Remote Sensing, vol. GE-22, no. 2, pp. 113-120, Mar. 1984. https://doi.org/10.1109/TGRS.1984.350602