| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 527573 | Image and Vision Computing | 2007 | 10 Pages |
Abstract
Farsi character recognition (FCR) systems perform recognition of Farsi documents. This paper presents a novel approach of fast Farsi character recognition based on fast zernike wavelet moments and artificial neural networks. Fast Zernike wavelet moments and artificial neural networks are employed in feature extraction and classification, respectively. A simulation result shows superiority of novel scheme over similar ones in terms of precision 4.37 times in average, and improves recognition speed by about 8.0 times in average.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Ali Broumandnia, Jamshid Shanbehzadeh,