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

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

Document Image Binarization Using a Water Flow Model

Water Flow Model을 이용한 문서 영상의 이진화

  • 김인권 (서강대학교 전자공학과) ;
  • 정동욱 (서강대학교 전자공학과) ;
  • 송정희 (서강대학교 영상대학원 Media 공학과) ;
  • 박래홍 (서강대학교 전자공학과)
  • Published : 2001.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a local adaptive thresholding method based on a water flow model, in which an image surface is considered as a 3-dimensional (3-D) terrain. To extract characters from backgrounds, we pour water onto the terrain surface. Water flows down to the lower regions of the terrain and fills valleys. Then, the amount of filled water is thresholded, in which the proposed thresholding method is applied to gray level document images consisting of characters and backgrounds. The proposed method based on a water flow model shows the property of locally adaptive thresholding. Computer simulation with synthetic and real document images shows that the proposed method yields effective adaptive thresholding results for binarization of document images.

본 논문에서는 영상의 밝기 값을 마치 3차원 지형과 같은 개념으로 간주하여 여기에 물이 흐르는 개념을 적용하여 국부 적응 (locally adaptive) thresholding 방법을 제안하였다. 문자를 추출해내기 위해 제안한 방법에서는 지형 표면에 물을 붓는 과정을 수행하였다. 물은 지형의 낮은 곳으로 흐르게 되어 계곡 (valley)에 쌓인다. 이때 문자와 배경으로 구성된 문서영상에서 쌓인 물의 양을 기준으로 두 개의 영역을 구분을 하였다. 제안한 water flow model의 개념을 적용한 threholding 방법은 국부 적응 thresholding의 특성을 나타낸다. 합성 영상과 실제 영상을 이용하여 전산 모의 실험을 수행함으로써 제안한 방법이 문서 영상을 효과적으로 이진화할 수 있음을 보였다.

Keywords

References

  1. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley, New York, 1992
  2. N. Otsu, 'A threshold selection method from gray-level histograms,' IEEE Trans. Systems, Man, Cybernetics, vol. SMC-9, no. 1, pp. 62-66, 1979
  3. Y. Nakagawa and A. Rosenfeld, 'Some experiments on variable thresholding,' Pattern Recognition, vol. 11, pp. 191-204, 1979
  4. S. U. Lee, S. Y. Chung, and R.-H. Park, 'A comparative performance study of several global thresholding techniques for segmentation,' Computer Vision, Graphics, Image Processing, vol. 52, no. 2, pp. 171-190, 1990 https://doi.org/10.1016/0734-189X(90)90053-X
  5. P. K. Sahoo, A. K. C. Wong, and Y. C. Chen, 'A survey of thresholding techniques,' Computer Vision, Graphics, Image Processing, vol. 41, no. 2, pp. 233-260, 1988 https://doi.org/10.1016/0734-189X(88)90022-9
  6. T. Pavlidis and Y.-T. Liow, 'Integrating region growing and edge detection,' IEEE Trans. Pattern Anal. Machine Intell, vol. PAMI-12, no. 3, pp. 225-233, 1990 https://doi.org/10.1109/34.49050
  7. L. Vincent and P. Soille, 'Watersheds in digital space: An efficient algorithm based on immersion simulations,' IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-13, no. 6, pp. 583-598, 1991
  8. H. Ancin et al., 'An improved watershed algorithm for counting objects in noisy, anisotropic 3-D biological images,' in Proc. 1995 IEEE Int. Conf. Image Processing, vol. I, pp. 172-175, Washington D.C.,USA, 1995 https://doi.org/10.1109/ICIP.1995.537608
  9. T. Geraud et al., 'Segmenting internal structures in 3D MR images of the brain by Markovian relaxation on a watershed based adjacency graph,' in Proc. 1995 IEEE Int. Conf. Image Processing, vol. II, pp. 548-551, Washington D.C.,USA, 1995 https://doi.org/10.1109/ICIP.1995.537693
  10. M. Baccar, L. A. Gee, R. C. Gonzalez, and A. Abidi, 'Segmentation of range images via data fusion and morphological watersheds,' Pattern Recognition, vol. 29, no. 10, pp. 1673-1687, 1996 https://doi.org/10.1016/0031-3203(96)00022-2
  11. P. T. Jackway, 'Gradient watersheds in morphological scale-space,' IEEE Trans. Image Processing, vol. IP-5, no. 6, pp. 913-921, 1996 https://doi.org/10.1109/83.503908
  12. L. Najaman and M. Schmitt, 'Geodesic saliency of watershed contours and hierarchical segmentation,' IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-18, no. 12, pp. 1163-1173, 1996 https://doi.org/10.1109/34.546254
  13. C. K. Lee and S. P. Wong, 'Morphological approach for thresholding noisy images,' in Proc. SPIE Visual Communication and Image Processing, vol. 2501, pp. 1773-1784, Taipei,Taiwan, 1995 https://doi.org/10.1117/12.206713
  14. N. Paparnarkos and B. Gatos, 'A new approach for multilevel threshold selection,' Graphical Models Image Processing, vol. 56, no. 5, pp. 357-370, 1994 https://doi.org/10.1006/gmip.1994.1034
  15. L. O'Gorman, 'Binarization and multithresholding of document images using connectivity,' Graphical Models Image Processing, vol. 56, no. 6, pp. 494-506, 1994 https://doi.org/10.1006/gmip.1994.1045
  16. A. Beghdadi, A. L. Negrate, and P. V. De Lesegno, 'Entropic thresholding using a block source model,' Graphical Models Image Processing, vol. 57, no. 3, pp. 197-205, 1995 https://doi.org/10.1006/gmip.1995.1019
  17. O. D. Trier, T. Taxt, and A. K. Jain, 'Recognition of digits in hydrographic maps-binary versus topographic analysis,' IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-19, no. 4, pp. 399-404, 1997 https://doi.org/10.1109/34.588025
  18. Y. Liu and S. N. Srihari, 'Document image binarization based on texture features,' IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-19, no. 5, pp. 540-544, 1997 https://doi.org/10.1109/34.589217
  19. O. D. Trier and T. Taxt, 'Evaluation of binarization methods for document images,' IEEE Trans. Pattern Anal. Machine intell., vol. PAMI-17, no. 3, pp. 312-315, 1995 https://doi.org/10.1109/34.368197
  20. W. Niblack, An introduction to Digital Image Processing, Prentice Hall, New Jersey, 1986
  21. O. D. Trier and A. K. Jain, 'Goal-directed evaluation of binarization methods,' IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-17, no. 12, pp. 1191-1201, 1995 https://doi.org/10.1109/34.476511
  22. S. D. Yanowitz and A. M. Bruckstein, 'A new method for image segmentation,' Computer Vision, Graphics, Image Processing, vol. 46, no. 1, pp. 82-95, 1989 https://doi.org/10.1016/S0734-189X(89)80017-9
  23. D.-G. Sim, Y. K. Ham, I. K. Kim, and R.-H. Park, 'Analysis of mixed Korean document using the branch and bound algorithm based on DP matching,' Computer Vision and Image Understanding, vol. 71, no. 3, pp. 373-384, 1998 https://doi.org/10.1006/cviu.1997.0651
  24. Computer Vision and Image Understanding v.71 no.3 Analysis of mixed Korean document using the branch and bound algorithm based on DP matching D.G.Sim;Y.K.Ham;I.K.Kim;R.H.Park