Abstract
Many problems in early vision can be formulated in terms of minimizing a cost function. Examples are shape from shading, edge detection, motion analysis, structure from motion, and surface interpolation. As shown by Poggio and Koch [Poggio, T. & Koch, C. (1985) Proc. R. Soc. London, Ser. B 226, 303-323], quadratic variational problems, an important subset of early vision tasks, can be "solved" by linear, analog electrical, or chemical networks. However, in the presence of discontinuities, the cost function is nonquadratic, raising the question of designing efficient algorithms for computing the optimal solution. Recently, Hopfield and Tank [Hopfield, J. J. & Tank, D. W. (1985) Biol. Cybern. 52, 141-152] have shown that networks of nonlinear analog "neurons" can be effective in computing the solution of optimization problems. We show how these networks can be generalized to solve the nonconvex energy functionals of early vision. We illustrate this approach by implementing a specific analog network, solving the problem of reconstructing a smooth surface from sparse data while preserving its discontinuities. These results suggest a novel computational strategy for solving early vision problems in both biological and real-time artificial vision systems.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Ballard D. H., Hinton G. E., Sejnowski T. J. Parallel visual computation. Nature. 1983 Nov 3;306(5938):21–26. doi: 10.1038/306021a0. [DOI] [PubMed] [Google Scholar]
- Hopfield J. J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci U S A. 1984 May;81(10):3088–3092. doi: 10.1073/pnas.81.10.3088. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Hopfield J. J., Tank D. W. "Neural" computation of decisions in optimization problems. Biol Cybern. 1985;52(3):141–152. doi: 10.1007/BF00339943. [DOI] [PubMed] [Google Scholar]
- Kirkpatrick S., Gelatt C. D., Jr, Vecchi M. P. Optimization by simulated annealing. Science. 1983 May 13;220(4598):671–680. doi: 10.1126/science.220.4598.671. [DOI] [PubMed] [Google Scholar]
- Koch C., Poggio T., Torre V. Retinal ganglion cells: a functional interpretation of dendritic morphology. Philos Trans R Soc Lond B Biol Sci. 1982 Jul 27;298(1090):227–263. doi: 10.1098/rstb.1982.0084. [DOI] [PubMed] [Google Scholar]
- Marr D., Poggio T. A computational theory of human stereo vision. Proc R Soc Lond B Biol Sci. 1979 May 23;204(1156):301–328. doi: 10.1098/rspb.1979.0029. [DOI] [PubMed] [Google Scholar]
- Poggio T., Torre V., Koch C. Computational vision and regularization theory. 1985 Sep 26-Oct 2Nature. 317(6035):314–319. doi: 10.1038/317314a0. [DOI] [PubMed] [Google Scholar]