Back to Search
Start Over
A Neural-Network-Based Approach to Optical Symbol Recognition.
- Source :
- Neural Processing Letters; Apr2002, Vol. 15 Issue 2, p117-135, 19p
- Publication Year :
- 2002
-
Abstract
- In this paper we propose a neural-network-based approach to solving optical symbol recognition problems, from node head recognition to handwritten digit recognition. We demonstrated that node heads could be easily recognized by using a set of fuzzy rules extracted from the parameters of trained neural networks. For handwritten digit recognition we demonstrated that only 12 features are sufficient to achieve a high recognition rate. Several databases were tested to demonstrate the effectiveness and efficiency of the proposed recognition method. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 13704621
- Volume :
- 15
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- Neural Processing Letters
- Publication Type :
- Academic Journal
- Accession number :
- 51589388
- Full Text :
- https://doi.org/10.1023/A:1015288717988