Abstract | ||
---|---|---|
A pattern recognition system mainly contains two functional parts, i.e. feature extraction and pattern classification. The success of such a system depends on not only the effectiveness of each of them, but also their operation in concert. The feature extraction process in a traditional recognition system has two major tasks, namely, to extract deformation invariant signals and to reduce data. When a neural network is used as a pattern classifier, however, an alteration in these basic objectives is needed. In particular, the consideration of data reduction will be replaced by that of the suitability of feature vectors to the neural network. In this paper, feature extraction algorithms in character recognition have been designed based on these principles. The improvements made by these algorithms have been demonstrated in a series of experiments which justify such a change in the fundamental objectives of the feature extraction process when an associative memory classifier is used. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1142/S0218001496000232 | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
feature extraction, associative memory, neural networks, pattern recognition, Chinese character recognition | k-nearest neighbors algorithm,Feature vector,Content-addressable memory,Pattern recognition,Feature (computer vision),Computer science,Feature extraction,Feature (machine learning),Artificial intelligence,Classifier (linguistics),Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
10 | 4 | 0218-0014 |
Citations | PageRank | References |
4 | 0.51 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
ming zhang | 1 | 4 | 0.51 |
Ching Y. Suen | 2 | 7569 | 1127.54 |
T. D. Bui | 3 | 78 | 18.52 |