IEICE Trans - Generation of Training Data by Degradation Models for Traffic Sign Symbol Recognition

Generation of Training Data by Degradation Models for Traffic Sign Symbol Recognition

Hiroyuki ISHIDA
Tomokazu TAKAHASHI
Ichiro IDE
Yoshito MEKADA
Hiroshi MURASE

Publication
IEICE TRANSACTIONS on Information and Systems Vol.E90-D No.8 pp.1134-1141
Publication Date: 2007/08/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e90-d.8.1134
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Image Recognition and Understanding)
Category:
Keyword:
traffic sign recognition, generative learning method, genetic algorithm, car-mounted camera,

Full Text: PDF(688.9KB)>>

Summary:
We present a novel training method for recognizing traffic sign symbols. The symbol images captured by a car-mounted camera suffer from various forms of image degradation. To cope with degradations, similarly degraded images should be used as training data. Our method artificially generates such training data from original templates of traffic sign symbols. Degradation models and a GA-based algorithm that simulates actual captured images are established. The proposed method enables us to obtain training data of all categories without exhaustively collecting them. Experimental results show the effectiveness of the proposed method for traffic sign symbol recognition.

open access publishing via