Title :
An analog VLSI neural network character recognition system: the feature extraction module
Author :
Caviglia, Daniele D. ; Rossi, Annamaria ; Vincentelli, Mario ; Valle, Maurizio
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
Abstract :
In this paper we present the analog architecture of a VLSI feature extraction module for a neural network based optical character recognition system. The algorithm for features extraction is mapped on analog circuit primitives and the computation is fully analog. The analog solution gives an efficient implementation and high performances. The complete circuit and physical design of the module is presented. The design has been verified through intensive circuit simulations
Keywords :
VLSI; OCR system; analog VLSI neural network; analog architecture; character recognition system; circuit simulations; feature extraction module; Analog circuits; Analog computers; Character recognition; Computer architecture; Feature extraction; Neural networks; Optical character recognition software; Optical computing; Optical fiber networks; Very large scale integration;
Conference_Titel :
Microelectronics for Neural Networks and Fuzzy Systems, 1994., Proceedings of the Fourth International Conference on
Conference_Location :
Turin
Print_ISBN :
0-8186-6710-9
DOI :
10.1109/ICMNN.1994.593712
