Paper Info
Title
Traffic sign classification by image preprocessing and neural networks
Abstract
The aim of this work is to design a Traffic Sign Classification system that combines different image preprocessing techniques with Neural Networks. It must be robust against image problems like rotation, deterioration, vandalism, and so on. The preprocessings applied to the gray scale transformed image are: the median filter (MF), the histogram equalization (HE), and the vertical (VH) and horizontal (HH) histograms with fixed or variable (mean value or Otsu method) thresholding. The k-Nearest Neighbour (k-NN) classifier is used for comparison purposes. The best performance is obtained with the combination of preprocessings: MF, HE and VH and HH with a fixed threshold (T = 185), with a two hidden layer MultiLayer Perceptron (MLP), which achieves a probability of classification of 98, 72% for nine different classes of blue traffic signs and noise. The performance is better than the classifier based on one hidden layer MLP in at least 1, 28% and based on k-NN in at least 5, 13%. If computational cost must be reduced, other preprocessings with a one hidden layer MLP are proposed, which performance is lower.
Year
DOI
Venue
2007
10.1007/978-3-540-73007-1_89
IWANN
Keywords
Field
DocType
hidden layer,neural network,best performance,different image,hidden layer mlp,fixed threshold,image problem,neural networks,traffic sign classification,multilayer perceptron,different class,otsu method,image preprocessing,classification system,median filter,histogram equalization
Histogram,Median filter,Pattern recognition,Computer science,Otsu's method,Multilayer perceptron,Artificial intelligence,Thresholding,Artificial neural network,Histogram equalization,Grayscale,Machine learning
Conference
Volume
ISSN
Citations 
4507
0302-9743
0
PageRank 
References 
Authors
0.34
8
5
Name
Order
Citations
PageRank
raul vicenbueno1557.55
A. García-González200.34
E. Torijano-Gordo300.34
roberto gilpita4577.79
Manuel Rosa-Zurera519236.27