Title :
Finding arrows in utility maps using a neural network
Author :
den Hartog, J.E. ; ten Kate, T.K.
Author_Institution :
TNO Inst. of Appl. Phys., Delft
Abstract :
In this paper a new technique is proposed for the reliable classification of poor quality arrows in hand drawn utility maps. The classification uses a neural network which is trained to distinguish arrows from other line symbols. A line symbol is represented by a feature vector based on the pseudo-Euclidean distances along the skeleton. The classification is evaluated with an independent test set
Keywords :
neural nets; hand drawn utility maps; line symbol; neural network; poor quality arrows; pseudo-Euclidean distances; reliable classification; Computer applications; Computer graphics; Computer networks; Intelligent networks; Neural networks; Physics; Pixel; Shape; Skeleton; Testing;
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
DOI :
10.1109/ICPR.1994.576902
