Handwritten Character Recognition to Obtain Editable Text in Optical Character Recognition

Abstract

To develop a web application for character recognition. Reading the text from an image is not achieved totally with all the technology we have even now and this is a big area for research. Generally the handwritten documents are saved in some format for future uses. A simple way to store the information is to capture images of the handwritten document and save it in image format or in pdf format. These saved data can be corrupted or may lose its clarity over time making the document non readable or non understandable. With the help of ‘Optical Character Recognition’ we can transform handwritten data into electronic format and save it in word format. It involves several steps including pre -processing, segmentation, feature extraction and post-processing. Many researchers have been using OCR for character  recognition. This system takes input of an image of the document or some URL where the document is available over the internet and further steps are done by OCR. The main challenge is to recognize the characters from different styles of handwriting. Thus, a system is designed that recognizes the handwritten data to obtain an editable text. The output of this system depends upon the data that has to be written by the writer. Our system offers 90% accuracy for handwritten documents and gives the easiest way to edit or share the recognized data.