A connectionist classifier architecture applied to image segmentation

Published 4 December 2002

W. E. Blanz, Sheri L. Gish

DOI10.1109/icpr.1990.119369

Citations31

TL;DR

The performance of a complete system, including pixel descriptor extraction and connectionist classifier, is demonstrated using scenes from industrial inspection and combustion chamber research tasks.

Abstract

A connectionist classifier architecture that is used in an image segmentation scheme based upon a decision analysis paradigm is described. An appropriate architecture for a connectionist classifier is discussed, and its relationship to other image segmentation architectures following the same paradigm is shown. The performance of a complete system, including pixel descriptor extraction and connectionist classifier, is demonstrated using scenes from industrial inspection and combustion chamber research tasks.>

Keywords

Computer Science

The MIT Press eBooksParallel Distributed Processing

15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more

Journal of the Royal Statistical Society Series A (General)Pattern Classification and Scene Analysis.

3,240 Citations1974Mairi Clarke, Richard O. Duda +1 more

IEEE Transactions on Systems Man and CyberneticsNeocognitron: A neural network model for a mechanism of visual pattern recognition

700 Citations1983Kunihiko Fukushima, Sei Miyake +1 more

A recognition with a large-scale network is simulated on a PDP-11/34 minicomputer and is shown to have a great capability for visual pattern recognition and can be trained to recognize handwritten Arabic numerals even with considerable deformations in shape.

Nonparametric feature selection for multiple class processes

10 Citations2003W. E. Blanz

A method of feature selection is presented that has linear computational complexity, and ways are shown how to use it when the type of the probability density function is unknown.

Springer series in perception engineeringControl-Free Low-Level Image Segmentation: Theory, Architecture, and Experimentation

9 Citations1989W. E. Blanz, Jorge L. C. Sanz +1 more

Experimentation with many different industrial problems proves that this approach is an effective and useful building block for low-level computer vision applications.

Machine Vision and ApplicationsCombined decision theoretic and syntactic approach to image segmentation

7 Citations1989B. Straub, W. E. Blanz

It is shown how statistical properties of iconic information can be systematically used to program a special architecture for parallel decision theoretic image segmentation that can resolve ambiguities and incomplete segmentation results in cases where objects and background are not clearly distinct by textural and gray level properties alone.

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>VLSI-oriented architectures for real-time image processing</title>

1 Citations1990W. E. Blanz

Two different VLSI and architectural approaches to the decision analysis part of a complex low level image segmentation architecture (LISA) are investigated, a modification of a classical statistical classifier and a connectionist approach using a layered feed forward net.

View PDF