Optical Character Recognition Based Webapp

Abstract

As the use of computers in our daily lives increases, so has the need for a natural procedure to interact with the computers. The ultimate aim of human computer interaction is to bring the change that there is always a natural way of interacting with computers coupled with ease and flexibility. Printed and textual media such as prescriptions, invoices, receipts, etc. occupies a large segment of our day-to-day activities and given their volume, it is inefficient to manage them physically as there’s always an associated risk of fading, damage, misplacing, etc. and hence a medium is required for their digital conversion. In this project, we have developed a robust, cross-platform web application that can process the images using PyTesseract based algorithms that can efficiently extract the textual data to facilitate the storage and retrieval of the same. The extracted text can be downloaded as a text file and can also be translated into the desired language. This is an active field of research and thus this paper also discusses various current implementations of the mentioned concept. The Optical Character Recognition framework finds applications in a variety of fields such as business process activities, number plate recognition, KYC and banking processes to name a few.