Title :
Analog design of a new neural network for optical character recognition
Author :
Morns, Ian P. ; Dlay, Satnam S.
Author_Institution :
Dept. of Electr. & Electron. Eng., Newcastle upon Tyne Univ., UK
fDate :
7/1/1999 12:00:00 AM
Abstract :
An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy
Keywords :
analogue processing circuits; feedforward neural nets; handwritten character recognition; neural chips; optical character recognition; Fourier descriptors; classification accuracy; handwritten numerals; recognition rate; wavelet descriptors; Backpropagation; Character recognition; Electronic circuits; Negative feedback; Neural networks; Neurons; Optical character recognition software; Optical computing; Optical design; Optical fiber networks;
Journal_Title :
Neural Networks, IEEE Transactions on
