Wavelet-based text recognition

Abstract

Text recognition is one of the most popular practical applications of character pattern recognition. The first step is to acquire a digital image. The next stage is segmentation, the pattern recognition problem can be represented into data acquisition, preprocessing, feature extraction, and classification. The wavelet transform is used in including image processing. Wavelet transform produces a low frequency sub band image reflecting its basic shape and three sub band images that contain the high frequency components of the image at horizontal, vertical and diagonal directions. The artificial neural networks have successfully used. In this project, wavelet coefficients are used in numeral recognition problem, these features are fed to Multilayer Perceptron network which is used as a classifier.