Traffic sign recognition with VG-RAM Weightless Neural Networks

Author

Berger, Marcel ; Forechi, Avelino ; Souza, A.F.D. ; de Oliveira Neto, Jorcy ; Veronese, Lucas ; Badue, Claudine

Author_Institution

Dept. de Inf., Univ. Fed. do Espirito Santo, Vitoria, Brazil

fYear

2012

fDate

27-29 Nov. 2012

Firstpage

315

Lastpage

319

Abstract

Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training and test. In this paper, we present a new approach for traffic sign recognition based on VG-RAM WNN. We evaluate its performance using the German Traffic Sign Recognition Benchmark (GTSRB), a large multi-class classification benchmark. Our experimental results showed that our VG-RAM WNN architecture for traffic sign recognition was able to rank at 4th position in the GTSRB evaluation system, with a recognition rate of 98.73%, and was overcome by only one automatic approach.

Keywords

benchmark testing; learning (artificial intelligence); neural net architecture; optical character recognition; random-access storage; traffic engineering computing; GTSRB performance evaluation system; German traffic sign recognition benchmark; VG-RAM WNN architecture; machine learning technique; multiclass classification benchmark; recognition rate; virtual generalizing random access memory weightless neural network architecture; Benchmark testing; Biological neural networks; Computer architecture; Neurons; Random access memory; Training; German Traffic Sign Recognition Benchmark; Traffic Sign Recognition; VG-RAM Weightless Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems Design and Applications (ISDA), 2012 12th International Conference on

Conference_Location

Kochi

ISSN

2164-7143

Print_ISBN

978-1-4673-5117-1

Type

conf

DOI

10.1109/ISDA.2012.6416557

Filename

6416557