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

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

A New Preprocessing Method for the Seedup of the Watershed-based Image Segmentation

분수계 기반 영상 분할의 속도 개선을 위한 새로운 전처리 방법

  • Cho, Sang-Hyun (School of Electronic and Electrical Engineering, Kyungpook National University) ;
  • Choi, Heung-Moon (School of Electronic and Electrical Engineering, Kyungpook National University)
  • 조상현 (경북대학교 전자전기공학부) ;
  • 최흥문 (경북대학교 전자전기공학부)
  • Published : 2000.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a new preprocessing method is proposed to speedup the watershed-based image segmentation In the proposed method, the gradient correction values of ramp edges are calculated from the positions and width of the ramp edges using Laplacian operator, and then, unlike the conventional method in which the monoscale or multi scale gradient image is directly used as a reference iImage, the reference image is obtained by adding the threshold value to each position of the ramp edges in the monoscale gradient image And the marker image is reconstructed on the reference image by erosion By preprocessing the image for the watershed transformation in such a manner, we can reduce the oversegmentations far more than those of applying the conventional morphological filter to the simple monoscale or multiscale gradient-based reference image Thus, we can reduce the total image segmentation time by reducing the time of postprocessing of region merging, which consumes most of the processing time In the watershed-based image segmentation, Experimental results indicate that the proposed method can speedup the total image segmentation about twice than those of the conventional methods, without the loss of ramp edges and principal edges around the dense-edge region.

본 논문에서는 분수계 기반 영상 분할의 속도 개선을 위한 새로운 전처리 방법을 제안하였다 영상 분할을 위한 분수계 변환에 있어서, 단순히 단일척도 또는 다중척도의 형태학적 기울기 연산자를 사용하여 만드는 기존의 기준 영상과는 달리, 제안한 방법에서는 원 영상에 라플라시안 연산을 수행해 램프 에지의 위치와 에지 폭을 구한후 이로부터 램프 에지 기울기 보정값을 구하였다 그런후, 단일척도 기울기 연산자를 사용한 영상에 이들 램프 에지의 위치에만 보정값을 더하여 기준 영상을 만들었다 여기에 마커 영상을 만들어 부식에 의해 재구성하여 얻은 영상을 분수계 변환함으로써, 단일 또는 다중 척도 기울기 연산에 의한 기준 영상을 사용한 경우보다 과분할을 방지할 수 있어서, 분수계 기반 영상 분할 처리 시간의 대부분을 차지하는 영역 병합을 대폭 줄여 총 영상 분할 시간을 단축하였다 기존의 방법들과의 비교 실험을 통하여 제안한 방법은 램프 에지나 에지 밀집 지역의 주요 에지들의 소실 없이 과분할을 줄여 전체 영상 분할 속도를 약 2배 가까이 향상시킬 수 있음을 확인하였다

Keywords

References

  1. R. Pal and K. Pal, 'A review on image segmentation technique,' Pattern Recognition, vol. 26, pp 1277-1294, 1993 https://doi.org/10.1016/0031-3203(93)90135-J
  2. R. Harahck and L. Shapiro, 'Survey Image segmentation technique,' Computer Vision Graphic and Image Processing, vol. 29, pp. 100-132, Jan. 1985 https://doi.org/10.1016/S0734-189X(85)90153-7
  3. L. Vincent and P. Soille, 'Watersheds in digital spaces An efficient algorithm based on immersion simulations,' IEEE Trans. Pattern Analysis and Machine Interlligence, vol. 13, no 6, Jun. 1991 https://doi.org/10.1109/34.87344
  4. P. Salembier and M. Paras, 'Hierarchical morphological segmentation for image sequence coding,' IEEE Trans on Image Processing, vol. 3, no. 5, pp. 369-651, Sep. 1994 https://doi.org/10.1109/83.334980
  5. J. and P. Soille, 'Morphological gradients,' Journal of Electronic Imaging, vol. 2, no. 4, pp. 326-336, Oct. 1993 https://doi.org/10.1117/12.159642
  6. J. Thiran, L. Vincent, and B. Macq, 'A queue-based region growing algorithm for accurate segmentation of multi-dimensional digital images,' Signal Processing, vol. 60, pp. 1-10, 1997 https://doi.org/10.1016/S0165-1684(97)00060-1
  7. L. Shafarenko and M. Petrou, 'Automatic watershed segmentation of randomly textured color image,' IEEE Trans. on Image Processing, vol 6, no. 11, pp. 1530-1543, Nov. 1997 https://doi.org/10.1109/83.641413
  8. 유한민, 이경무, '조건부 확장연산과 Watershed 알고리듬을 이용한 영상객체 분할기법,', 신호처리합동학술대회 논문지, vol. 11, no 1, pp. 103-106, Oct. 1998
  9. K. Haris, S. Efstratiadis, N. Maglaveras, and C. Pappas, 'Hybrid image segmentation using watershed,' SPIE Proc. Visual Communications and Image Processing 96, pp. 1140-1151, Orlando, Florida, U.S.A., March, 1996 https://doi.org/10.1117/12.233186
  10. P. Salembier, 'Morphological multiscale segmentation for image coding,' Signal Processing, vol. 38, no. 3, pp. 359-386, July 1994 https://doi.org/10.1016/0165-1684(94)90155-4
  11. D. Wang, 'A multiscale gradient algorithm for image segmentation using watersheds,' Pattern Recognition, vol. 30, no. 12, pp. 2043-2052, 1997 https://doi.org/10.1016/S0031-3203(97)00015-0
  12. L. Gupta and T. Sortrakul, 'A gaussian-mixture image segmentation algorithm,' Pattern Recognition, vol. 3, no. 3, pp. 315-325, 1998 https://doi.org/10.1016/S0031-3203(97)00045-9
  13. L. Vincent, 'morphological grayscale reconstruction in image analysis. Applications and efficient algonthm,' Signal Processing, vol. 2, no. 2, pp. 176-201, Apr. 1993
  14. P. Salembier and P. Brigger, 'morphological operators for image and video compression,' IEEE Trans. Image Processing, vol. 5, no. 6, pp. 881-898, June 1996 https://doi.org/10.1109/83.503906
  15. P. Salembier, Luis Garrido, and David Garcia, 'Image Sequence Analysis and Merging Algorithm', European Signal Processing Conference, Rhodes, Greece, vol.3, pp. 1693-1696, Sep. 1998