Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

An adaptive Fuzzy Binarization

적응 퍼지 이진화

  • Jeon, Wang-Su (Dept. of IT Convergence Engineering, Kyungnam University) ;
  • Rhee, Sang-Yong (Dept. of Computer Engineering, Kyungnam University)
  • 전왕수 (경남대학교 IT융합공학과) ;
  • 이상용 (경남대학교 컴퓨터공학과)
  • Received : 2016.11.16
  • Accepted : 2016.12.19
  • Published : 2016.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

A role of the binarization is very important in separating the foreground and the background in the field of the computer vision. In this study, an adaptive fuzzy binarization is proposed. An ${\alpha}$-cut control ratio is obtained by the distribution of grey level of pixels in a sliding window, and binarization is performed using the value. To obtain the ${\alpha}$-cut, existing thresholding methods which execution speed is fast are used. The threshold values are set as the center of each membership function and the fuzzy intervals of the functions are specified with the distribution of grey level of the pixel. Then ${\alpha}$-control ratio is calculated using the specified function and binarization is performed according to the membership degree of the pixels. The experimental results show the proposed method can segment the foreground and the background well than existing binarization methods and decrease loss of the foreground.

이진화는 컴퓨터 비전 분야에서 전경과 배경을 분리하는 중요한 역할을 한다. 본 연구에서는 적응 퍼지 이진화 방법을 제안한다. 이동 창 내의 화소의 밝기 값 분포에 따라 ${\alpha}$-컷을 구하고, 이 값을 이용하여 이진화를 수행한다. ${\alpha}$-컷을 구하기 위해 수행속도가 빠른 기존의 이진화 방법들을 이용한다. 기존 방법들로 구해진 임계치들을 퍼지 소속 함수들의 중심값으로 설정하고, 화소의 밝기값 분포를 이용하여 퍼지 소속 함수들의 구간을 결정한다. 결정된 퍼지 소속 함수들을 이용하여 ${\alpha}$-컷의 조정율을 구하고, 각 화소의 소속도에 따라 이진화를 수행한다. 실험 결과는 제안한 방법이 기존의 방법들보다 전경과 배경이 효과적으로 분리될 수 있고, 전경의 손실이 적어지는 것을 보여준다.

Keywords

References

  1. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing 3rded, Prentice Hall, 2008.
  2. N. Otsu, "A threshold selection method from gray-level histograms," IEEE Trans. Syst. Man Cybernet, vol. 9, pp. 62-66, 1979. https://doi.org/10.1109/TSMC.1979.4310076
  3. K. Y. Kim, "A Thresholding Method for Defference Image Using Fuzzy Inference," J. of the Korea Institute of Intelligent Systems Society, vol. 9, no.3, pp. 352-359, 1999.
  4. K. B. Kim, "ART2 Based Fuzzy Binarization Method withLow Information Loss," Journal of the Korea Institute of Information and Communication Engineering, vol. 18, no.6, pp. 1269-1274, 2014. https://doi.org/10.6109/jkiice.2014.18.6.1269
  5. A. K. Wassim, K. Seifedine, B. Riccardo and S. Khaled, "Accurate, Swift and Noiseless Image Binarization," Stat, Optim. Inf. Comput. vol. 4, pp. 42-56, 2016.
  6. H. C. Lee, K. B. Kim, H. J. Park and E. Y. Cha, "An $\alpha$ - cut Automatic Set based on Fuzzy Binarization Using Fuzzy Logic," J. of the Korea Institute of Information and Communication Engineering, vol. 19, no. 12, pp. 2924-2932, 2015. https://doi.org/10.6109/jkiice.2015.19.12.2924
  7. D. H. Kim and E. Y. Cha, "Binarization and Stroke Reconstruction of Low Quality Character Image for Effective Character Recognition," Korea Institute of Maritime Information and Communication, vol. 11, no. 3, pp. 608-618, 2007.
  8. M. Negnevitsky, Artificial Intelligence 2nd ed, Hanbitmedia, 2011.
  9. S. K. Oh, Computational Intelligence by Programming focused on Fuzzy, Neural networks, and Genetic Algorithms, Naeha, 2005.
  10. W. Niblack, An introduction to digital image processing, Prentice-Hall, Englewood Cliffs, N. J., pp. 115-116, 1986.
  11. J. Sauvola, "M. Pietikainen, Adaptive document image binarization," Pattern Recognition, vol. 33 pp. 225-236, 2000. https://doi.org/10.1016/S0031-3203(99)00055-2
  12. A. Jain, Fundamentals of Digital Image Processing, Prentice-Hall, Englewood Cliffs, N. J., pp. 409, 1986.