About this document

Braille Recognition Using CNN Technology by Zath Onam is a document available to read on EtoBox.

This document summarizes a research article that presents a novel approach for optical braille recognition (OBR) using convolutional neural networks (CNNs). The goal is to reduce asymmetric communication between blind and non-blind individuals by allowing non-blind people to understand braille. A new dataset of over 26,000 labeled braille images was created, representing 37 braille symbols corresponding to 71 English characters. A CNN model was trained on this data and achieved 98.73% prediction accuracy on

Author

Zath Onam

Language

EN