Automation of Snake for Extraction of Multi-Object Contours from a Natural Scene

자연배경에서 여러 객체 윤곽선의 추출을 위한 스네이크의 자동화

  • 최재혁 (LG전자 전자설계팀) ;
  • 서경석 (경북대학교 전자공학과) ;
  • 김복만 (경북대학교 전자공학과) ;
  • 최흥문 (경북대학교 전자전기컴퓨터공학부)
  • Published : 2003.12.01

Abstract

A novel multi-snake is proposed for efficient extraction of multi-object contours from a natural scene. An NTGST(noise-tolerant generalized symmetry transform) is used as a context-free attention operator to detect and locate multiple objects from a complex background and then the snake points are automatically initialized nearby the contour of each detected object using symmetry map of the NTGST before multiple snakes are introduced. These procedures solve the knotty subjects of automatic snake initialization and simultaneous extraction of multi-object contours in conventional snake algorithms. Because the snake points are initialized nearby the actual contour of each object, as close as possible, contours with high convexity and/or concavity can be easily extracted. The experimental results show that the proposed method can efficiently extract multi-object contours from a noisy and complex background of natural scenes.

자연배경으로부터 불특정 다수 객체의 윤곽선들을 자동 추출하는 다중 스네이크(Snake) 알고리즘을 제안하였다. 먼저 잡음에 강건한 문맥자유 주목연산자(context-free attention operator)를 이용하여 자연배경에 혼재하는 불특정 다수 객체들을 자동 검출하고, 각 객체별로 스네이크의 초기 윤곽들을 자동 설정함으로써 기존 스네이크 알고리즘에서는 어려웠던 초기 윤곽의 자동 설정과 여러 객체 윤곽선의 동시 추출 문제를 해결하였다. 이때 각 스네이크의 초기 윤곽들은 기존의 방법들에 비해 객체들의 실제윤곽선에 좀 더 가까이 설정하여 요철이 큰 객체들의 윤곽선도 쉽게 추출 할 수 있도록 하였다. 다양한 합성 영상과 자연배경의 실영상에 대해 실험하여 잡음이 있는 복잡한 배경으로부터도 불특정 다수 객체의 윤곽선을 효과적으로 자동 추출함을 확인하였다.

Keywords

References

  1. D. Reisfeld, H. Wolfson, and Y. Yeshurun, 'Context-free attentional operators: The generalized symmetry transform,' IJCV, vol. 14, pp. 119-130, Jan. 1995 https://doi.org/10.1007/BF01418978
  2. C. J. Park, S. H. Cho, and H. M. Choi, 'An Implementation of Noise-Tolerant Context-free Attention Operator and its Application to Efficient Multi-Object Detection,' IEEK Trans., vol. 38SP, no. 1, pp. 89-96, Jan. 2001
  3. K. S .Seo, C. J. Park, S. H. Cho, and H. M. Choi, 'Context-free marker-controlled watershed transform for efficient multi-object detection and segmenatation,' IEEE Trnas. on Fundamentals, vol. E84-A, no. 6, June 2001
  4. P. K. Sahoo, S. Soltani, A. K. C. Wong, and Y. C. Chen, 'A survey of thresholding techniques,' CVGIP, vol. 41, pp. 233-260, 1988 https://doi.org/10.1016/0734-189X(88)90022-9
  5. M. Kass, A. Witkin, and D. Terzopoulos, 'Snakes: Active Contour Models,' Int. J. Comp. Vision, vol. 1, pp. 321-331, 1988 https://doi.org/10.1007/BF00133570
  6. P. C. Yuen, Y. Y. Wong, and C. S. Tong, 'Enhanced snakes algorithm for contour detection,' Proc. of the IEEE Southwest Symp. on Image Analysis and Interpretation, pp. 54-59, 1996 https://doi.org/10.1109/IAI.1996.493726
  7. Y. Y. Wong, P. C. Yuen and C. S. Tong, 'Segmented snake for contour detection,' Pattern Recognition, vol. 31, no. 11, pp. 1669-1679, 1998 https://doi.org/10.1016/S0031-3203(98)00048-X
  8. H. J. Lee, S. H. Cho, and H. M. Choi, 'An automatic extraction of blood flow contour from cardiac MRI,' IEEK Trans., vol. 37SC, no. 5, pp. 56-62, sep 2000
  9. Williams, Donna and Shah, Mubarak, 'A Fast Algorithm for Active Contours and Curvature Estimation,' CVGIP: Image Understanding, vol. 55, no.1, pp. 14-26, Jan. 1992 https://doi.org/10.1016/1049-9660(92)90003-L
  10. K. M. Lam, and H. Yan, 'Fast greedy algorithm for active contours,' Electron Lett., vol. 30, pp. 21-23, 1994 https://doi.org/10.1049/el:19940040
  11. Wai-Park Choi, Kin-Man Lam, and Wan-Chi Siu, 'An adaptive active contour model for highly irregular boundaries,' Pattern Recognition, vol. 34, pp. 323-331, 2001 https://doi.org/10.1016/S0031-3203(99)00231-9