This Article 
 Bibliographic References 
 Add to: 
The Integration of Image Segmentation Maps using Region and Edge Information
December 1993 (vol. 15 no. 12)
pp. 1241-1252

We present an algorithm that integrates multiple region segmentation maps and edge maps. It operates independently of image sources and specific region-segmentation or edge-detection techniques. User-specified weights and the arbitrary mixing of region/edge maps are allowed. The integration algorithm enables multiple edge detection/region segmentation modules to work in parallel as front ends. The solution procedure consists of three steps. A maximum likelihood estimator provides initial solutions to the positions of edge pixels from various inputs. An iterative procedure using only local information (without edge tracing) then minimizes the contour curvature. Finally, regions are merged to guarantee that each region is large and compact. The channel-resolution width controls the spatial scope of the initial estimation and contour smoothing to facilitate multiscale processing. Experimental results are demonstrated using data from different types of sensors and processing techniques. The results show an improvement over individual inputs and a strong resemblance to human-generated segmentation.

[1] C. W. Tong, S. K. Rogers, J. P. Mills, and M. K. Kabrisky, "Multisensor data fusion of laser radar and forward looking infrared (FLIR) for target segmentation and enhancement,"Proc. SPIE, vol. 782, pp. 10-19, May 1987.
[2] B. Bhanu and R. D. Holben, "Model-based segmentation of FLIR images,"IEEE Trans. Aerospace Electron. Syst., vol. 26, no. 1, pp. 2-11, Jan. 1990.
[3] C. Chu, N. Nandhakumar, and J. K. Aggarwal, "Image segmentation using laser radar data,"Patt. Recogn., vol. 23, no. 6, pp. 569-581, 1990.
[4] C. Chu and J. K. Aggarwal, "Interpretation of laser radar images by a knowledge-based system,"J. Machine Vision Applications, no. 4, pp. 145-163, 1991.
[5] C. Chu and J. K. Aggarwal, "Multisensor image interpretation using laser radar and thermal images," inProc. Seventh Conf. Artificial Intell. Applications, (Miami Beach, FL), Feb. 24-28, 1991, pp. 190-196.
[6] C. Chu and J. K. Aggarwal, "The integration of region and edge-based segmentation," inProc. Third Int. Conf. Comput. Vision(Osaka, Japan), Dec. 4-7, 1990, pp. 117-120.
[7] M. D. Levine and A. M. Nazif, "Low level image segmentation: an expert system,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-6, no. 5, pp. 555-577, Sept. 1985.
[8] P. Fua and A. J. Hanson, "Using generic geometric models for intelligent shape extraction," inProc. DARPA Image Understanding Workshop, Los Angeles, CA, Feb. 1987, pp. 227-233.
[9] A. Toet, "Hierarchical image fusion,"J. Machine Vision Applications, vol. 3, no. 1, pp. 1-11, 1990.
[10] R. R. Kohler, "Integrating non-semantic knowledge into image segmentation process," Univ. of Massachusetts, Amherst, COINS Tech. Rep. 84-04, 1984.
[11] A. C. Bovik, "On detecting edges in speckle imagery,"IEEE Trans. Acous. Speech., Signal Processing, vol. 36, no. 10, pp. 1618-1627, Oct. 1988.
[12] H. L. Anderson, R. Bajcsy, and M. Mintz, "A modular feedback system for image segmentation," Univ. of Pennsylvania, Philadelphia, GRASP Lab Tech. Rep. 110, June 1987.
[13] T. Pavlidis and Y. T. Liow, "Integrating region growing and edge detection,"IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 3, pp. 225-233, Mar. 1990.
[14] J. F. Haddon and J. F. Boyce, "Image segmentation by unifying region and boundary information,"IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 3, pp. 929-948, Oct. 1990.
[15] R. C. Luo, M. Lin, and R. S. Scherp, "The issues and approaches of a robot multi-sensor integration," inProc. IEEE Robotics Automation Conf., Mar. 31-Apr. 3, 1987, pp. 1941-1946.
[16] Y. Nakamura and Y. Xu, "Geometrical fusion method for multi-sensor robotic systems,"Proc. IEEE Int. Conf. Robotics Automat., Scottsdale, AZ, 1989, pp. 668-673.
[17] D. Sher, "Evidence combination using likelihood generators," inProc. DARPA Image Understanding Workshop, Los Angeles, CA, Feb. 1987, pp. 655-662.
[18] D. Marr,Vision. San Francisco, CA: W. H. Freeman, 1982, pp. 62-63.
[19] B. Shahraray and D. J. Anderson, "Optimal estimation of contour properties by cross-validated regularization,"IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 6, pp. 600-610, June 1989.
[20] M. D. Srinath and P. K. Rajasenkaran,An Introduction to Statistical Signal Processing with Applications. New York: Wiley, 1979.
[21] H. L. Van Trees,Detection, Estimation, and Modulation Theory, Vol. I. New York: Wiley, 1968.
[22] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models," inProc. 1st Int. Conf. Computer Vision, London, England, June 8-11, 1987, pp. 259-268.
[23] C. G. Bachman,Laser Radar Systems and Techniques. Dedham, MA: Artech House, 1979.
[24] D. C. Baker, S. S. Hwang, and J. K. Aggarwal, "Detection and segmentation of man-made objects in outdoor scenes: concrete bridges,"J. Opt. Soc. Amer., vol. 6, no. 6, pp. 938-950, June 1989.

Index Terms:
image segmentation maps; region/edge maps; information integration; edge detection; region segmentation modules; maximum likelihood estimator; edge pixels; iterative procedure; contour curvature; contour smoothing; multiscale processing; edge detection; filtering and prediction theory; image segmentation; iterative methods; optimisation; probability
C.C. Chu, J.K. Aggarwal, "The Integration of Image Segmentation Maps using Region and Edge Information," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 12, pp. 1241-1252, Dec. 1993, doi:10.1109/34.250843
Usage of this product signifies your acceptance of the Terms of Use.