Title :
An efficient digital architecture for character recognition
Author :
Gioiello, M. ; Sorbello, F. ; Tarantino, A. ; Vassallo, G.
Author_Institution :
Dipartimento di Ingegneria Elettrica, Palermo Univ., Italy
Abstract :
We introduce a new digital neural architecture designed for automatic hand-written characters recognition. The architecture implements a two-layer perceptron off-line trained by conjugate gradient descent algorithm and the final weights are quantized and stored in a RAM. The architecture was developed and tested using the VHDL Alliance 2.0 CAD System simulator: it is easy to implement using standard VLSI technologies and may be used to deal with multi-level inputs
Keywords :
character recognition; computer architecture; conjugate gradient methods; hardware description languages; neural net architecture; perceptrons; VHDL Alliance 2.0 CAD System simulator; automatic hand-written characters recognition; character recognition; conjugate gradient descent algorithm; digital architecture; multi-level inputs; neural architecture; two-layer perceptron; Character recognition; Chromium; Circuits; Databases; Design automation; Minimization; Multilayer perceptrons; NIST; Standards development; System testing;
Conference_Titel :
Computer Architectures for Machine Perception, 1995. Proceedings. CAMP '95
Conference_Location :
Como
Print_ISBN :
0-8186-7134-3
DOI :
10.1109/CAMP.1995.521031
