Overview
In this report, a functional real time vision based on American sign language recognition for D&M people have been developed for ASL alphabets.
We achieved an accuracy of 95.7% on our dataset.
Prediction has been improved after implementing two layers of algorithms in which we verify and predict symbols which are more similar to each other.
Approach
The approach taken is applying image filtering with OpenCV to get the processed image after feature extraction.
This processed image is passed to Convolutional Neural Networks (CNN) model for prediction and if a letter is detected for more than 50 frames.
We detect various symbols and show similar results via detection.
The University of Sydney
Vishant Prasad