skip to content
An Analog Model of Computation for the Ill-Posed Problems of Early Vision. Preview this item
ClosePreview this item
Checking...

An Analog Model of Computation for the Ill-Posed Problems of Early Vision.

Author: T Poggio; C Koch; MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB.
Publisher: Ft. Belvoir Defense Technical Information Center MAY 1984.
Edition/Format:   Book : English
Database:WorldCat
Summary:
A large gap exists at present between computational theories of vision and their possible implementation in neural hardware. The model of computation provided by the digital computer is clearly unsatisfactory for the neurobiologist, given the increasing evidence that neurons are complex devices, very different from simple digital switches. It is especially difficult to imagine how networks of neurons may solve the  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

 

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Document Type: Book
All Authors / Contributors: T Poggio; C Koch; MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB.
OCLC Number: 227629587
Description: 18 p.

Abstract:

A large gap exists at present between computational theories of vision and their possible implementation in neural hardware. The model of computation provided by the digital computer is clearly unsatisfactory for the neurobiologist, given the increasing evidence that neurons are complex devices, very different from simple digital switches. It is especially difficult to imagine how networks of neurons may solve the equations involved in vision algorithms in a way similar to digital computers. In this paper, we suggest an analog model of computation in electrical or chemical networks for a large class of vision problems, that maps more easily into biologically plausible mechanisms. Poggio and Torre have recently recognized that early vision problems such as motion analysis, edge detection, surface interpolation, shape-from shading and stereo matching can be characterized as mathematically ill-posed problems. Ill-posed problems can be solved, according to regularization theories, by variational principles of a specific type. A natural way of implementing variational problems are electrical, chemical or neuronal networks. We present specific networks for solving several low-level vision problems, such as the computation of visual motion and edge detection.

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


<http://www.worldcat.org/oclc/227629587>
library:oclcnum"227629587"
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/227629587>
rdf:typeschema:Book
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:about
schema:contributor
schema:contributor
schema:contributor
schema:datePublished"1984"
schema:datePublished"MAY 1984"
schema:description"A large gap exists at present between computational theories of vision and their possible implementation in neural hardware. The model of computation provided by the digital computer is clearly unsatisfactory for the neurobiologist, given the increasing evidence that neurons are complex devices, very different from simple digital switches. It is especially difficult to imagine how networks of neurons may solve the equations involved in vision algorithms in a way similar to digital computers. In this paper, we suggest an analog model of computation in electrical or chemical networks for a large class of vision problems, that maps more easily into biologically plausible mechanisms. Poggio and Torre have recently recognized that early vision problems such as motion analysis, edge detection, surface interpolation, shape-from shading and stereo matching can be characterized as mathematically ill-posed problems. Ill-posed problems can be solved, according to regularization theories, by variational principles of a specific type. A natural way of implementing variational problems are electrical, chemical or neuronal networks. We present specific networks for solving several low-level vision problems, such as the computation of visual motion and edge detection."@en
schema:exampleOfWork<http://worldcat.org/entity/work/id/1909338270>
schema:inLanguage"en"
schema:name"An Analog Model of Computation for the Ill-Posed Problems of Early Vision."@en
schema:numberOfPages"18"
schema:publisher
schema:url

Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.