This document reviews a system for text recognition using convolutional neural networks. The system uses an artificial neural network and nearest neighbor concepts to develop an optical character recognition (OCR) engine. The OCR engine takes images as input and converts them to soft copies through various processing stages, including preprocessing, segmentation, character recognition, and error detection and correction. It aims to improve on existing OCR engines by reducing errors. The system is intended to be implemented as an Android app to allow offline conversion of printed texts to soft copies. It reviews the methodology and various components of the proposed system, including the neural network architecture and training approach.