Summary
This article deals with a neural network based on Min/Max nodes and its utilisation for image recognition purposes. The general concepts of the Min/Max nodes and the single-layer neural networks are outlined. The developed software systems for simulation are briefly introduced and the results of simulations with the various settings of a neural net are presented. The subject of simulations was the recognition of human faces. Finally, the hardware design of the neural network in VHDL is shown. The design demonstrates the ease of systems realisation and the achieving of high performance.
See the full content of this document
Extract
Software and Hardware Realisation of Neural Network Based On Min/Max Nodes for Image Recognition
1. Introduction
At present there is a large development of the image recognition systems. One of the possibilities is utilization of neural nets. This possibility has been the main subject of cooperation between the Department of Applied Electronics and Telecommunications, University of West Bohemia and the Department of Electrical and Electronic Engineering (now Electronic and Computer Engineering) at Brunei University over the past decade.This cooperation has been mainly focused on the neural nets with n-tuple nodes [1] and MIN/MAX nodes [2, 3]. The network of the MIN/MAX nodes could respond directly to multi-level values and so it could provide powerful pattern recogni...See the full content of this document
Sponsored links
