Title :
A fuzzy ARTMAP module for graphics symbols recognition
Author :
Murshed, Nabeel A. ; Bortolozzi, Flavio
Author_Institution :
LADIANN, Pontificia Univ. Catolica do Parana, Curtiba, Brazil
Abstract :
This paper presents a method for recognizing graphics symbols of electronic components in a database of circuit layouts. The method is based on the one-class problem approach on our ability to recognize a 2D-objects without making an explicit decomposition. To satisfy these requirements, a fuzzy ARTMAP recognition module was developed with the objective of recognizing the graphics symbols of 19 electronic components. Each fuzzy ARTMAP was trained with 2D images of graphic symbols of one component only (positive patterns only). The recognition module was then used to search for a specific component in a database of 30 images of circuit layouts. The training and test sets contained respectively, 380 images (2D images/component), and 2051 images (an average of 108 images/component). Experimental results show an average percentage error of 3.49%
Keywords :
ART neural nets; circuit diagrams; circuit layout CAD; document image processing; fuzzy neural nets; image recognition; visual databases; 2D object recognition; circuit layouts; database; electronic components; fuzzy ARTMAP module; graphics symbols recognition; neural net; one-class problem; Circuits; Graphics; Image analysis; Image databases; Image recognition; Layout; Neural networks; Pattern recognition; Shape; Text analysis;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687112
