Considerations of vision based on associative neural networks

Valeriu C. Beiu, Sorin Georgescu

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The authors consider vision from a neural-network (NN) point of view. After describing the structure of the human retina and its neurons, a general model of NNs is presented. For color, patterns, and motion detection, a three-layer NN is detailed. Further, three variable-threshold NNs (color identification) are introduced. The detection of motion is also done in this second layer using already preprocessed information represented by on-off, on, and off signals, with the same meaning as the corresponding signals from the human ganglion cells; four analog classifiers are used for directions (up, down, left, right). The results of a program used to simulate the proposed NN are discussed, as well as a theoretical VLSI implementation. It is shown that a complete graph having n nodes can be laid out in an almost square area of O(n2), with O(n) wire length.

Original languageEnglish
Title of host publicationVLSI and Computer Peripherals
EditorsWalter E. Proebster, Hans Reiner, W. Schilz, C. Butterworth, E. Lueder, al et al
PublisherPubl by IEEE
ISBN (Print)0818619406
Publication statusPublished - 1989
Externally publishedYes
EventCOMPEURO '89 - 3rd Annual European Computer Conference - Hamburg, West Ger
Duration: May 8 1989May 12 1989

Publication series

NameVLSI and Computer Peripherals


OtherCOMPEURO '89 - 3rd Annual European Computer Conference
CityHamburg, West Ger

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Considerations of vision based on associative neural networks'. Together they form a unique fingerprint.

Cite this