Toggle Main Menu Toggle Search

Open Access padlockePrints

The DSFPN: A New Neural Network and Circuit Simulation for Optical Character Recognition

Lookup NU author(s): Ian Morns, Emeritus Professor Satnam Dlay


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


A new type of neural network for recognition tasks is presented in this paper. The network, which is called the "dynamic supervised forward-propagation network" (DSFPN), is based on the forward only version of the counterpropagation network (CPN). The novel DSFPN trains using a supervised algorithm and can grow dynamically during training, allowing allographs in the training data to be learned in an unsupervised manner. Training times are comparable with the CPN while giving better classification accuracies than the popular multilayer perceptron (MLP). Data preprocessed using Fourier descriptors show that on average, the DSFPN trains in 1353 times fewer presentations than the MLP networks and gives best recognition accuracy of 98.6%. Moreover, data preprocessed using wavelet multiresolution analysis gives a very high recognition accuracy; the best accuracy is 99.792%. Results show the effectiveness of the DSFPN and justify a hardware implementation to enable fast data classification. Therefore, a circuit implementation for the DSFPN competitive middle layer is presented, and simulation results show that it can perform reliable pattern recognition at a rate of over 100 kHz.

Publication metadata

Author(s): Morns IP, Dlay SS

Publication type: Article

Publication status: Published

Journal: IEEE Transactions on Signal Processing

Year: 2003

Volume: 51

Issue: 12

Pages: 3198-3209

ISSN (print): 1053-587X

ISSN (electronic): 1941-0476

Publisher: IEEE


DOI: 10.1109/TSP.2003.819009


Altmetrics provided by Altmetric