Name
Title | ||
|---|---|---|
A comparative study of neural network algorithms applied to optical character recognition |
Abstract | ||
|---|---|---|
Three simple general purpose networks are tested for pattern classification on an optical character recognition problem. The feed-forward (multi-layer perceptron) network, the Hopfield network and a competitive learning network are compared. The input patterns are obtained by optically scanning images of printed digits and uppercase letters. The resulting data is used as input for the networks with two-state input nodes; for others, features are extracted by template matching and pixel counting. The classification capabilities of the networks are compared with a nearest neighbour algorithm applied to the same feature vectors. The feed-forward network reaches the same recognition rates as the nearest neighbour algorithm, even when only a small percentage of the possible connections is used. The Hopfield network performs less well, and overloading of the network remains a problem. Recognition rates with the competitive learning network, if input patterns are clustered well, are again as high as the nearest neighbour algorithm. |
Year | DOI | Venue |
|---|---|---|
1990 | 10.1145/98894.99119 | IEA/AIE (Vol. 1) |
Keywords | Field | DocType |
input pattern,hopfield network,simple general purpose network,comparative study,two-state input node,neural network,nearest neighbour algorithm,recognition rate,classification capability,optical character recognition problem,feed-forward network,competitive learning network,feature vector,feed forward,template matching,competitive learning,optical character recognition | Nearest neighbour algorithm,Competitive learning,Computer science,Time delay neural network,Feature (machine learning),Artificial intelligence,Artificial neural network,Feature vector,Pattern recognition,Algorithm,Perceptron,Hopfield network,Machine learning | Conference |
ISBN | Citations | PageRank |
0-89791-372-8 | 3 | 0.63 |
References | Authors | |
1 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| P. Patrick Van Der Smagt | 1 | 274 | 35.19 |
| universiteit van amsterdam | 2 | 75 | 26.97 |