Smart Cam: An Empowering Communication with Flask-Powered Image-to-Text Conversion

Abstract

Today, many of us go outside of the state or
country for jobs or holidays. Each location or
area may have their regional communication
language because of which a communication
gap may occur. Due to communication gaps,
people often are not able to communicate with
native people or perceive the written notes or
sign boards and typically don't seem to be
ready to do their work. This becomes a big
hurdle for many people who need a quick
solution. However, with the advancement of
technology, it is possible to use some
techniques to fill this communication gap by
translating images into text. The concept of
text-to-image offer user-friendly and efficient
communication between human and
computer (machine) that too in natural
languages. This paper proposed a web
application that translates the image into a
native language as per the user’s need. The
web-based application is developed with a
flask with numerous libraries such as
PyTesseract, OpenCV, Numpy, and textblob
libraries. The proposed work is based on
Tesseract. Tesseract is an OCR engine that
relies on Unicode and can recognize more
than 100 languages. The proposed work helps
the employee or tourist to visit foreign
countries or other places whose language is
not known or understandable to the person.