Title:	VIDEO IMAGE SPEED LIMIT SIGN DETECTION IN VARIOUS CONDITIONS USING NEURAL NETWORKS
Author(s):	Tomislav Fištrek, Sven Lon?ari?
ISBN:	978-972-8939-22-9
Editors:	Yingcai Xiao, Tomaz Amon and Piet Kommers
Year:	2010
Edition:	Single
Keywords:	Pattern recognition, image analysis, segmentation, traffic sign detection, artificial neural networks, feature extraction
Type:	Short Paper
First Page:	433
Last Page:	438
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this paper, we present a method for traffic sign detection based on an artificial neural network. The system extracts features necessary for the detection of a road sign. Searching of the image is performed by extracting various features, and by scanning. Color is taken as an important feature. Experimental results included several neural networks that are compared. The influence of the different choice of features and their combinations is investigated as well. This paper also wants to test the new additional step which precedes the segmentation, and it is the automatic sorting of input images in one of the groups according to the lighting. The purpose of this step is to show that in this way a bigger adaptability of the system is obtained, thus this way will enable traffic sign detection even in poor lighting conditions. Experimental procedure checks the stated hypotheses.
	Go Back