Title :
Neural network for connected character recognition
Author :
Fukushima, Kunihiko
Author_Institution :
Fac. of Eng. Sci., Osaka Univ., Toyonaka, Japan
Abstract :
A connected character recognition system using an architecture based on the selective attention model of a neural network is described. The discussion covers pattern recognition, segmentation, repairing imperfect patterns, attention focusing, search control, attention switching, size and position information, and computer simulation. Improvement of the system by the introduction of bend-detection cells is noted
Keywords :
character recognition; image reconstruction; image segmentation; neural nets; parallel architectures; architecture; attention focusing; attention switching; bend detection cells; computer simulation; connected character recognition; imperfect pattern repairing; neural network; search control; segmentation; selective attention model; Character recognition; Deformable models; Feature extraction; Handwriting recognition; Image segmentation; Neural networks; Pattern recognition; Robustness;
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-4260-2
DOI :
10.1109/ANNES.1993.323077
