A High Precision Line Detection Based on Local Area CCT Method

국소영역 내의 CCT법을 이용한 고정밀 직선 검출

  • 정남채 (초당대학교 정보통신공학과)
  • Received : 2013.02.25
  • Accepted : 2013.04.30
  • Published : 2013.04.30

Abstract

A detection method of high precision digital line within image is proposed in this paper. If we set the size of image to $N{\times}N$, in fact it is difficult to use the resulting values that the amount of computation is $O(N^4)$. Multiple algorithms are examined to reduced the amount of computation to $O(N^3)$, while suppressing the degradation of precision. How to detect line from the image processing, after stretching treatment of line segments extracted by Hough transform in the local area of an image is a great way to be able to detect several long or short line at high speed, but this method is slightly less precision in the detection of tilted line segments. In this paper, a line detection method improving the precision detection of tilted line segment is applied to the local area, thereby this method does not reduce the processing speed, while it is high precision method for detecting line segments. The experimental results confirm that the proposed method can detect a high precision line in a shorter period of time, compared with the existing methods.

본 논문에서는 화상에 존재하는 디지털 직선을 고정밀도로 검출하는 방법을 제안한다. 화상의 크기를 $N{\times}N$로 하면, 이 계산량은 $O(N^4)$이지만 실제 사용하기는 곤란하므로, 검출 정밀도의 열화를 억제하면서 계산량을 $O(N^3)$로 하는 알고리즘을 검토하였다. 국소영역에서 Hough 변환하여 추출된 선분을 연신처리(stretching treatment)하고, 화상으로부터 직선을 검출하는 방법은 길거나 짧은 여러 가지의 직선을 고속으로 검출할 수 있는 훌륭한 방법이지만, 기울어진 선분의 검출 정밀도는 약간 떨어진다. 본 논문에서는 사선의 검출 정밀도를 향상시킨 직선 검출방법을 국소영역에 적용함으로써 처리속도가 감소되지 않고, 직선을 고정밀도로 검출하는 방법에 관해서 논술한다. 실험 결과 제안된 방법은 기존의 방법과 같은 정도 이하의 시간에서 정밀도가 높은 직선을 검출할 수 있다는 것을 확인하였다.

Keywords

References

  1. R. O. Duda and P. E. Hart, "Use of the Hough transformation to detect lines and curves in pictures," Commun. ACM, vol. 15, no. 1, pp. 11-15, 1972 https://doi.org/10.1145/361237.361242
  2. P. K. Ser, W. C. Siu, "Invariant Hough transform with matching technique for the recognition of non-analytic objects," IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, pp. 9-12, vol. 5, April 1993
  3. Pawan Kumar, Virendra Singh, "Efficient regular expression pattern matching for network intrusion detection systems using modified word-based automata," Proc. 5th Int'l Conf. Security of Information and Networks (SIN '12), pp. 103-110, Oct. 2012
  4. 정남채, "RANSAC에 기초한 화면내 평면 영역 샘플링에 의한 스테레오 화상의 대응 매칭," 한국신호처리시스템학회논문지, v.12, no.4, 242-249, 2011
  5. Wang Min, Zhang Yanning, "Hough Transform Relative Nonuniform Parameter Space for the Detection of Line Segments," Int'l Conf. Computer Science and Software Engineering, pp. 764-767, Dec. 2008
  6. M. Morimoto, S. Akamatsu, and Y. Suenaga, "A high-resolution Hough trasnsform using variable filter," Proc. ICPR '92, pp. 280-284, 1992
  7. S. Maji and J. Malik, "Object Detection Using a Max-Margin Hough Transform," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 529-539, Jan. 2009
  8. R. Okada, "Discriminative Generalized Hough Transform for Object Detection," Proc. 12th IEEE Int'l Conf. Computer Vision, pp. 773-784, March 2009
  9. I. D. Svalve, "Natural representations for straight lines and the Hough transform on discrete arrays,"" IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 9, pp. 941-950, Sept. 1989 https://doi.org/10.1109/34.35497
  10. Zhaoxia Fu,Yan Han, "A Circle Detection Algorithm Based on Mathematical Morphology and Chain Code," Int'l Conf. Computing, Measurement, Control and Sensor Network, pp. 253-256, July 2012
  11. R. L. Graham, D. E. Knuth, and O. Patashnik, Concrete Mathematics, 2nd ed., Addison-Wesley, 1994
  12. 後藤英昭, 阿曾弘具, "ハフ變換におけるパラメ―タの效 率的サンプリング間隔," 信學論(D-II), vol. J-81-D -II, no.4, pp.697-705, April 1998