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

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

Adaptive Error Diffusion for Text Enhancement

문자 영역을 강조하기 위한 적응적 오차 확산법

  • Published : 2006.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

This Paper proposes an adaptive error diffusioThis paper proposes an adaptive error diffusion algorithm for text enhancement followed by an efficient text segmentation that uses the maximum gradient difference (MGD). The gradients are calculated along with scan lines, and the MGD values are filled within a local window to merge the potential text segments. Isolated segments are then eliminated in the non-text region filtering process. After the left segmentation, a conventional error diffusion method is applied to the background, while the edge enhancement error diffusion is used for the text. Since it is inevitable that visually objectionable artifacts are generated when using two different halftoning algorithms, the gradual dilation is proposed to minimize the boundary artifacts in the segmented text blocks before halftoning. Sharpening based on the gradually dilated text region (GDTR) prevents the printing of successive dots around the text region boundaries. The error diffusion algorithm with edge enhancement is extended to halftone color images to sharpen the tort regions. The proposed adaptive error diffusion algorithm involves color halftoning that controls the amount of edge enhancement using a general error filter. The multiplicative edge enhancement parameters are selected based on the amount of edge sharpening and color difference. Plus, the additional error factor is introduced to reduce the dot elimination artifact generated by the edge enhancement error diffusion. By using the proposed algorithm, the text of a scanned image is sharper than that with a conventional error diffusion without changing background.

본 논문에서는 최대 기울기 차이(maximum gradient difference, MGD)를 이용한 효과적인 문자 분할과 문자 영역을 강조하기 위한 적응적 오차 확산법을 제안한다. 스캔 라인을 따라 기울기를 계산하고, 잠재적 문자 영역을 융합하기 위해 국부적 윈도우 내에 MGD 값을 채운다. 노이즈 필터링을 거친 후, 배경에는 기존 오차 확산법, 문자에는 경계 향상 오차 확산법을 적용한다. 서로 다른 하프토닝 알고리즘의 사용으로 눈에 거슬리는 결함이 발생하기 때문에 경계 결함을 줄이기 위해 단계적 팽창(gradual dilation)을 적용한다. 단계적으로 팽창된 문자 영역(gradually dilated to저 region, GDTR)에 기반한 샤프닝(sharpening)은 문자 영역의 경계에서 연속적으로 점이 찍히는 것을 막을 수 있다. 제안한 적응적 오차 확산법은 일반적인 오차 필터를 이용하여 경계 향상 정도를 조절할 수 있는 칼라 하프토닝 방법이다. 경계 향상 정도와 색차를 분석하여 경계 향상 계수를 정하고, 경계 향상 오차 확산법의 사용으로 인해 점이 찍히지 않는 결함을 줄이기 위하여 추가적인 오차 요소를 반영하였다. 스캔한 영상을 제안한 방법을 이용하여 하프토닝하면 배경의 변화 없이 문자 부분이 선명한 결과를 얻을 수 있다.

Keywords

References

  1. Y. Zhong, K. Karu, and A. Jain, 'Locating text in complex color images,' Pattern Recognition, vol. 28, no. 10, pp. 1523-1535, Oct. 1995 https://doi.org/10.1016/0031-3203(95)00030-4
  2. J. Ohya, A. Shio, and S. Akamatsu, 'Recognizing characters in scene images,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 2, pp. 214-220, Feb. 1994 https://doi.org/10.1109/34.273729
  3. D. Karatzas and A. Antonacopoulos, 'Two approaches for text segmentation in web images,' Proc. of Seventh International Conf. on Document Analysis and Recognition, 3-6, vol. 1, pp. 131-136, Aug. 2003 https://doi.org/10.1109/ICDAR.2003.1227646
  4. C. Strouthopoulos, N. Papamarkos, and A. E. Atsalakis, 'Text extraction in complex color documents,' Pattern Recognition, vol. 35, pp. 1743-1758, July 2002 https://doi.org/10.1016/S0031-3203(01)00167-4
  5. V. Wu, R. Manmatha, and E. M. Riseman, 'TextFinder: An automatic systems to detect and recognizing text in images,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 11, pp. 1224-1229, Nov. 1999 https://doi.org/10.1109/34.809116
  6. K. T. Knox, 'Evolution of error diffusion,' SPIE Conf. on Device-Independent Color Imaging, vol. 3648, pp. 448-458, Jan. 1999 https://doi.org/10.1117/12.334588
  7. E. K. Wong and M. Chen, 'A new robust algorithm for video text extraction,' Pattern Recognition, vol. 36, no. 1, pp. 1397-1406, 2002 https://doi.org/10.1016/S0031-3203(02)00230-3
  8. R. Ulicheney, Digital Halftoning, The MIT Press, 1993
  9. T. Mitsa and K. J. Parker, 'Digital halftoning technique using a blue-noise mask,' J. Opt. Soc. Am. A, vol. 9, no. 11, pp. 1920-1929, Nov. 1992 https://doi.org/10.1364/JOSAA.9.001920
  10. D. J. Lieberman and J. P. Allebach, 'A dual interpretation for direct binary search and its implications for tone reproduction and texture quality,' IEEE Trans. Image Processing, vol. 9, no. 11, pp. 1950-1963, Nov. 2000 https://doi.org/10.1109/83.877215
  11. R. W. Floyd and L. Steinberg, 'An adaptive algorithm for spatial greyscale,' Proc. Soc. Image Display, vol. 17, no. 2, pp. 75-77, 1976
  12. R. Eschbach and K. T. Knox, 'Error-diffusion algorithm with edge enhancement,' J. Opt. Soc. Am. A, vol. 8, no. 12, pp. 1844-1850, 1991 https://doi.org/10.1364/JOSAA.8.001844
  13. K. T. Knox, 'Error image in error diffusion,' Proc. SPIE Image Proc., vol. 1657, pp. 268-279, 1992 https://doi.org/10.1117/12.58334
  14. T. D. Kite, B. L. Evans, and A. C. Bovik, 'Modeling and quality assessment of halftoning by error diffusion,' IEEE Trans. Image Processing, vol. 9, no. 5, pp. 909-922, May 2000 https://doi.org/10.1109/83.841536
  15. Y. Hasan and L. Karam, 'Morphological text extraction from images,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 11, pp. 1978-1983, Nov. 2000 https://doi.org/10.1109/83.877220
  16. N. Otsu, 'A threshold selection method from gray-level histograms,' IEEE Trans. Systems, Man and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979 https://doi.org/10.1109/TSMC.1979.4310076
  17. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley, New York, 2002
  18. R. S. Berns, Principles of Color Technology, Wiley-Interscience Publication, 2000