Using fuzzy filters as feature detectors

Chuen-Tsai Sun*, Tsuey Yuh Shuai, Guang Liang Dai

*Corresponding author for this work

Research output: Contribution to conferencePaper

2 Scopus citations

Abstract

A neuro-fuzzy model of adaptive learning and feature detection is presented. The model, called the fuzzy filtered neural network, was first introduced in a previous publication, which showed its validity in the domain of plasma analysis. Here we extend the model to another problem, the recognition of hand-written numerals, to demonstrate its generality. We propose three versions of the architecture, which use one-dimensional fuzzy filters, two-dimensional fuzzy filters, and genetic-algorithm-based fuzzy filters, respectively, as feature detectors. All three versions smoothly handle such issues of a real-world pattern recognition problem as drifting and noise. Simulation results show that the proposed model is an efficient architecture for achieving high recognition accuracy.

Original languageEnglish
Pages406-410
Number of pages5
StatePublished - 1 Dec 1994
EventProceedings of the 3rd IEEE Conference on Fuzzy Systems. Part 3 (of 3) - Orlando, FL, USA
Duration: 26 Jun 199429 Jun 1994

Conference

ConferenceProceedings of the 3rd IEEE Conference on Fuzzy Systems. Part 3 (of 3)
CityOrlando, FL, USA
Period26/06/9429/06/94

Fingerprint Dive into the research topics of 'Using fuzzy filters as feature detectors'. Together they form a unique fingerprint.

Cite this