CNN based Optical Character Recognition and Applications

The procedure of translating images of handwritten, typewritten, or typed text into a format recognized by computers is called Optical Character Recognition (OCR). Editing, indexing, searching, and storage space reduction are the uses of Optical Character Recognition. This is done by scanning the picture of the text character-by-character first, then processing the scanned image and eventually converting the image of the character into character codes, such as ASCII. To translate text in an image into text format, the Optical Character Recognition system is used. There are three key aspects of OCR approach: pre-processing, character recognition, character segmentation and presentation of data. Convolutional Neural Network is a deep learning method which is used for character recognition. In this paper, CNN layers, architecture and implementation of CNN architecture are discussed. Here the CNN (VGG-16) model is trained over Telugu character data set which covers maximum of 1600 characters and its accuracy is measured.