Identification of Optimal Optical Character Recognition (OCR) Engine for Proposed System

A large number of research efforts have been put forward that attempts to transform a document image to format understandable for machine so that it can recognize the text or the information from the image. OCR i.e. Optical Character Recognition provides a solution for this. OCR is software that converts printed text and images into digitized form such that it can be manipulated by machine. OCR systems have established a niche place in pattern recognition. OCR has two categories, online and offline. The image of the scanned document goes through various stages like preprocessing, segmentation, feature extraction, etc. in order to retrieve the information from the image. OCR is also popular among the Android applications. Tesseract is one of the most widely used open source library for implementing OCR in Android application.