ENGLISH CURSIVE SCRIPT RECOGNITION

This system proposes a fast method for english cursive script recognition (ECSR) which presents three main contributions. The first one is Unwanted Lines Elimination Algorithm (ULEA) . After binarization the input image by using an adaptive thresholding, Unwanted Lines Elimination Algorithm (ULEA) is proposed to enhance the image. The second contribution is that our proposed ECSR method processes very low-resolution images taken by a scanner. After the vertical edges have been detected by ULEA, the most-like character details based on feature information are highlighted. Then, the sample region based on statistical and logical operations will be extracted. The third contribution is character classification is achieved by using support vector machines (SVMs). A database of 1080 characters was used to train and test the cursive character recognizer. SVMs compare notably better, in terms of recognition rates, with popular classifiers, SVM recognition rate is among the highest presented in the literature for cursive character recognition.