Optical Character Recognition using Convolutional Neural Network

Optical Character Recognition is the process of translating images of handwritten, typewritten, or printed text into a format understood by machines. The purposes of Optical Character Recognition are editing, indexing/searching, and reduction in storage size. This is achieved by first scanning the photo of the text character-by-character, then it is followed by analysis of the scanned image, and finally the translation of the character image into character codes, such as ASCII. In this paper, we have used segmentation algorithm to divide the image into lines, words and then characters. The characters are recognized using Convolutional Neural Network. The results obtained by Convolutional Neural Networks seems to be promising in recognizing the characters in comparison to results obtained through other machine learning algorithms such as Support Vector Machines and Artificial Neural Networks.