Author : Prof. Aniket Bhoyar, Prof. Alka Shrivastav, Satvik Khedkar, Pranav Purkar, Shrutika Mohod, Sanket Gotmare, and Vanshaj Nagdeve

This project attempts to classify any unique handwritten text in order to convert the text material to a digital format. To complete this objective, we used two different methods: direct word classification and separating each character. Converting text to audio using an optical character reader (OCR) with the help of state- of-the-art technology has solved the main problem of convenient communication. We know that listening is more interactive than reading a book. It is good that the system captures images and detects and recognizes text. OCR converts input images into editable text, allowing you to turn paper documents into editable and searchable documents. This can help reduce the physical space required to store document and significantly improve the work flow associated with those documents.

Keywords: Optical character recognition, translation, audio speech