Handwritten data detection and secure data storage using deep learning and AES

Extracting textual information from natural images is a challenging problem
with many practical applications. Unlike character recognition for scanned
documents, recognizing text in unconstrained images is complicated by a wide
range of variations in backgrounds, textures, fonts, and lighting conditions.
The eld of machine learning is a rapidly developing one. Recognizing handwritten
text from images and storing isn't easy. It involves the diculty of
visual pattern recognition which becomes very apparent when an attempt is
made to write a computer program to recognize the text.This project seeks
to classify an individual handwritten character so that handwritten text can
be translated to a digital form. The goal of our project is to create a model
that should be able to recognize and determine the handwritten letters from
its image and store those data into an secured encryption format. We aim
to complete this by using the concepts of Convolution Neural Network and
AES.By implementing this we can easily store and search a data by using
machines.

MSC CS 2017-2019 INT Dr Tony Thomas