Poggio, Tomaso and Koch, Christof (1985) Ill-Posed Problems in Early Vision: From Computational Theory to Analogue Networks. Proceedings of the Royal Society of London. Series B, Biological Sciences, 226 (1244). pp. 303-323. ISSN 0962-8452. http://resolver.caltech.edu/CaltechAUTHORS:20130816-103221056
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20130816-103221056
We outline a theoretical framework that leads from the computational nature of early vision to algorithms for solving them and finally to a specific class of analogue and parallel hardware for the efficient solution of these algorithms. The common computational structure of many early vision problems is that they are mathematically ill-posed in the sense of Hadamard. Regularization analysis can be used to solve them in terms of variational principles of a specific type that enforce constraints derived from a physical analysis of the problem. Studies of human perception may reveal whether principles of a similar type are exploited by biological vision. We also show that the corresponding variational principles can be implemented in a natural way by analogue networks. Specific electrical and chemical networks for localizing edges and computing visual motion are derived. We suggest that local circuits of neurons may exploit this unconventional model of computation.
|Additional Information:||Received 5 September 1984 ; Revised 13 May 1985.|
|Group:||Koch Laboratory, KLAB|
|Official Citation:||Ill-Posed Problems in Early Vision: From Computational Theory to Analogue Networks T. Poggio and C. Koch Proceedings of the Royal Society of London. Series B, Biological Sciences , Vol. 226, No. 1244 (Dec. 23, 1985), pp. 303-323|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||KLAB Import|
|Deposited On:||26 Jan 2008 04:38|
|Last Modified:||24 Oct 2013 22:20|
Repository Staff Only: item control page