Fast Zernike wavelet moments for Farsi character recognition

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.