|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| N.S. Friedland, A. Rosenfeld, "Compact Object Recognition Using Energy-Function-Based Optimization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 7, pp. 770-777, July, 1992. | |||
| BibTex | x | ||
| @article{ 10.1109/34.142912, author = {N.S. Friedland and A. Rosenfeld}, title = {Compact Object Recognition Using Energy-Function-Based Optimization}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {14}, number = {7}, issn = {0162-8828}, year = {1992}, pages = {770-777}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.142912}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - Compact Object Recognition Using Energy-Function-Based Optimization IS - 7 SN - 0162-8828 SP770 EP777 EPD - 770-777 A1 - N.S. Friedland, A1 - A. Rosenfeld, PY - 1992 KW - 1D cyclic Markov random field; pattern recognition; energy-function-based optimization; polar coordinate; contour smoothness; edge sharpness; simulated annealing; Markov processes; pattern recognition; simulated annealing VL - 14 JA - IEEE Transactions on Pattern Analysis and Machine Intelligence ER - | |||
Describes a method of recognizing objects whose contours can be represented in smoothly varying polar coordinate form. Both low- and high-level information about the object (contour smoothness and edge sharpness at the low level and contour shape at the high level) are incorporated into a single energy function that defines a 1D, cyclic, Markov random field (1DCMRF). This 1DCMRF is based on a polar coordinate object representation whose center can be initialized at any location within the object. The recognition process is based on energy function minimization, which is implemented by simulated annealing.
[1] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models,"Int. J. Comput. Vision, vol. 1, pp. 321-331, 1988.
[2] P. Fua and A. J. Hanson, "Objective functions for feature discrimination: Theory," inProc. DARPA Image Understanding Workshop, 1989, pp. 443-460.
[3] P. Fua and A. J. Hanson, "Objective functions for feature discrimination: Applications to semiautomated and automated feature extraction," inProc. DARPA Image Understanding Workshop, 1989, pp. 676-694.
[4] R. G. Gallager,Information Theory and Reliable Communication. New York: Wiley, 1972, p. 80.
[5] A. Rosenfeld and A. Kak,Digital Picture Processing, New York: Academic, 1976.
[6] N. Friedland and D. Adam, "Automatic cavity boundary detection from sequential ultrasound images using simulated annealing,"IEEE Trans. Med. Imaging, vol. 8, pp. 344-353, 1989.
[7] S. Geman and D. Geman, "Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 721-741, 1984.
[8] N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller, and E. Teller, "Equation of state calculations by fast computing machines,"J. Chem. Phys., vol. 21, pp. 1087-1091, 1953.
[9] S. Kirkpatrick, C. D. Gelatt Jr., and M. P. Vecchi, "Optimization by simulated annealing," IBM Res. Rep. RC 9355, 1982.
[10] E. Ising,Zeitschrift Physik, vol. 31, p. 253, 1925; see, for example, C. J. Thompson,Mathematical Statistical Mechanics. New York: Macmillan, 1972.
[11] E. B. Baum, "Graph orthogonalization," to be published inDiscrete Mathematics.
[12] A. Margalit, "A parallel algorithm to generate a Markov random field image on a SIMD hypercube machine," CS-TR-2050, Cent. Automat. Res., Univ. of Maryland, College Park, 1988.
[13] G. H. Kornfeld, "Digital similation of precise sensor degradation including nonlinearities and shift variance," inProc. SPIE Infrared Image Processing Enhancement, vol. 781, pp. 63-70, 1987.