This Article 
 Bibliographic References 
 Add to: 
Boundary Detection and Skeletonization with a Massively Parallel Architecture
January 1990 (vol. 12 no. 1)
pp. 74-78

A massively parallel architecture called TOSCA (tokens sending cellular automation) is presented that performs edge pixel detection and skeletonization in the image processing area. Each cell of this cellular automaton has a very reduced set of instructions and a very small amount of memory. The computation is based on token propagation, counting devices, and local processing. The skeletonization method is based on the Chamfer distance.

[1] H. G. Barrow, J. M. Tenenbaum, R. C. Bolles, and H. C: Wolf, "Parametric correspondence and Chamfer matching: Two new techniques for image matching," inProc. IJCAI, 1977.
[2] G. Borgefors, "Matching edges in maps and aerial images using the Chamfer matching algorithm," Nat. Defense Res. Inst., Linkoping, Sweden, FOA Rep., Mar. 1983.
[3] G. Borgefors, "Distance transformation in arbitrary dimensions,"Comput. Vision, Graphics, Image Processing, vol. 21, pp. 321-345, 1984.
[4] P. E. Danielson, "Euclidean distance mapping,"Comput. Vision, Graphics, Image Processing, vol. 14, pp. 227-248, 1980.
[5] F. Devos, P. Garda, and B. Zavidovique, "Cellular hardware for a NCP based vision," inProc. CAPAIDM IEEE Comput. Soc. Workshop, Miami, FL, 1985.
[6] D. Hillis,The Connection Machine. Cambridge, MA: M.I.T. Press, 1985.
[7] M. Milgram and J. P. Cocquerez, "Fermeture des contours par un opérateur local,"Traitement du Signal, vol. 3, no. 6, 1986.
[8] M. Milgram, "Contribution aux réseaux d'automates," Thése d'Etat, Univ. Compiégne, France, 1982.
[9] U. Montanari, "A method for obtaining skeletons using a quasi-Euclidean distance,"J. Assoc. Comput. Machinery, vol. 15, pp. 600-624, Oct. 1968.
[10] S. Wolfram, "Universality and complexity of cellular automata," inCellular Automata, Proc. Interdisciplinary Workshop, Los Alamos, NM. Amsterdam, The Netherlands: North-Holland, 1983.
[11] A. M. Wood, "The interaction between hardware, software and algorithms," inLanguages and Architectures for Image Processing, M. J. B. Duff and S. Levialdi, Eds. New York: Academic, 1981.
[12] M. J. B. Duff, "Review of the CLIP image processing system," inProc. Nat. Computer Conf., Anaheim, CA, 1978.
[13] D. J. Hunt, "The ICL DAP and its application to image processing," inLanguage and Architectures for Image Processing, M. J. B. Duff and S. Levialdi, Eds. New York: Academic, 1981.
[14] J. L. Potter, "Continuous image processing on the MPP," inProc. IEEE Comput. Soc. Workshop Pattern Analysis and Image Database Managment, Hot Springs, VA, 1981.
[15] T. J. F. Fountain, "Further developments," inCellular Logic Image Processing, M. J. B. Duff and T. J. Fountain, Eds. New York: Academic, 1986.

Index Terms:
computerised pattern recognition; boundary detection; skeletonization; massively parallel architecture; TOSCA; edge pixel detection; cellular automaton; token propagation; counting devices; local processing; Chamfer distance; computerised pattern recognition; parallel architectures
M. Milgram, T. de Saint Pierre, "Boundary Detection and Skeletonization with a Massively Parallel Architecture," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 74-78, Jan. 1990, doi:10.1109/34.41385
Usage of this product signifies your acceptance of the Terms of Use.