Show simple item record

Analog "Neuronal" Networks in Early Vision

dc.date.accessioned2004-10-01T20:18:28Z
dc.date.accessioned2018-11-24T10:09:57Z
dc.date.available2004-10-01T20:18:28Z
dc.date.available2018-11-24T10:09:57Z
dc.date.issued1985-06-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/5654
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/5654
dc.description.abstractMany problems in early vision can be formulated in terms of minimizing an energy or cost function. Examples are shape-from-shading, edge detection, motion analysis, structure from motion and surface interpolation (Poggio, Torre and Koch, 1985). It has been shown that all quadratic variational problems, an important subset of early vision tasks, can be "solved" by linear, analog electrical or chemical networks (Poggio and Koch, 1985). IN a variety of situateions the cost function is non-quadratic, however, for instance in the presence of discontinuities. The use of non-quadratic cost functions raises the question of designing efficient algorithms for computing the optimal solution. Recently, Hopfield and Tank (1985) have shown that networks of nonlinear analog "neurons" can be effective in computing the solution of optimization problems. In this paper, we show how these networks can be generalized to solve the non-convex energy functionals of early vision. We illustrate this approach by implementing a specific network solving the problem of reconstructing a smooth surface while preserving its discontinuities from sparsely sampled data (Geman and Geman, 1984; Marroquin 1984; Terzopoulos 1984). These results suggest a novel computational strategy for solving such problems for both biological and artificial vision systems.en_US
dc.format.extent17 p.en_US
dc.format.extent3271888 bytes
dc.format.extent2548959 bytes
dc.language.isoen_US
dc.subjectanalog networksen_US
dc.subjectanalog-digital hardwareen_US
dc.subjectparallel computersen_US
dc.subjectssurface interpolationen_US
dc.subjectsurface reconstructionen_US
dc.subjectoptimization problemen_US
dc.subjectsregularization theoryen_US
dc.subjectearly visionen_US
dc.titleAnalog "Neuronal" Networks in Early Visionen_US


Files in this item

FilesSizeFormatView
AIM-751.pdf2.548Mbapplication/pdfView/Open
AIM-751.ps3.271Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record