文档介绍：Pattern Recognition Using Pulse-Coupled works and
Discrete Fourier Transforms
Raul C. Mureşan
Personal Research Center, P-ta Cipariu, Nr. 9, Ap. 17, Cluj-Napoca, Romania
******@,
Abstract
A novel method for pattern recognition using Discrete Fourier Transforms on the global pulse
signal of a pulse-coupled work (PCNN) is presented in this paper. We describe the
mathematical model of the PCNN and an original way of analyzing the pulse of work in
order to achieve scale- and translation-independent recognition for isolated objects. We also analyze
the error as a result of rotation. The system is used for recognizing simple geometric shapes and
letters.
Keywords: Pattern Recognition; Pulse-coupled works; Discrete Fourier Transform;
Multilayer perceptron.
1. Introduction
Pulse coupled works (PCNN) were introduced as a simple model for the cortical
neurons in the visual area of the cat's brain. Important research in the 80's and 90's led to the
establishment of a general model for PCNN [3]. Such models proved to be highly applicable in the
field of image processing, a series of optimal procedures being developed for contour detection and
especially image segmentation [10].
At the other end, image processing is faced with harder problems such as the pattern
recognition. Many recognition systems are based on sa