A Neural Network for Visual Pattern Recognition

Authors:
Kunihiko Fukushima
Affiliations:
NHK Science and Technical Research Laboratories, Tokyo, Japan
Venue:
Computer
Year:
1988

Citing 2
Cited 12

A neural network model for selective attention in visual pattern recognition

Biological Cybernetics
A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing

Selection of a neural network system for visual inspection

ACM SIGSIM Simulation Digest
Self organizing neural networks with a split/merge algorithm

SIGSMALL '90 Proceedings of the 1990 ACM SIGSMALL/PC symposium on Small systems
Performance comparison of neural networks and pattern recognition techniques for classifying ultrasonic transducers

SAC '92 Proceedings of the 1992 ACM/SIGAPP symposium on Applied computing: technological challenges of the 1990's
Original Contribution: Recognition and segmentation of connected characters with selective attention

Neural Networks
Neural ensembles: Simultaneous recognition of multiple 2-D visual objects

Neural Networks
Dynamic model of visual recognition predicts neural response properties in the visual cortex

Neural Computation
Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Figure–Ground Segregation in a Recurrent Network Architecture

Journal of Cognitive Neuroscience
Paper: Neurocomputers

Neurocomputing
Attractor memory with self-organizing input

BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology
Modeling the biological mechanisms of vision: Scan paths

Mathematical and Computer Modelling: An International Journal
Artificial vision by multi-layered neural networks: Neocognitron and its advances

Neural Networks

Quantified Score

Hi-index	4.11

Visualization

Abstract

A model of a neural network is presented that offers insight into the brain's complex mechanisms as well as design principles for information processors. The model has properties and abilities that most modern computers and pattern recognizers do not possess; pattern recognition, selective attention, segmentation, and associative recall. When a composite stimulus consisting of two or more patterns is presented, the model pays selective attention to each of the patterns one after the other, segments a pattern from the rest, and recognizes it separately in contrast to earlier models. This model has perfect associative recall, even for deformed patterns, without regard to their positions. It can be trained to recognize any set of patterns.