Loading...
Please wait, while we are loading the content...
Similar Documents
A Neural Network for Real-World Postal Address Recognition
| Content Provider | Semantic Scholar |
|---|---|
| Author | Blumenstein, Michael Verma, Brijesh |
| Copyright Year | 2007 |
| Abstract | In this paper, we present a description of an imple ented system for the recognition of printed and ha ndwritten postal addresses, based on Artificial Neural Networ ks (ANNs). Two classification methods were compared for the task of character and address recognition. We c ompared two neural network techniques, measuring recognition rate and accuracy. The C programming la u ge, a SUN workstation, and the SP2 Supercomput er were used for the experiments. The system has been successfully tested on real world printed and handw ritten postal addresses. Some experimental results are presented in this paper. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.int.gu.edu.au/~mblum/publications/WSC2.ps |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Addresses (publication format) Artificial neural network Biological Neural Networks Employer address:Addr:Pt:^Patient:Nom Experiment Linear algebra Postal Printing SUN workstation |
| Content Type | Text |
| Resource Type | Article |
