American Sign Language Alphabet Recognition using Deep Learning
This work addresses accessibility for deaf and hard-of-hearing individuals by enabling sign language recognition without expensive 3D cameras, though it is incremental as it applies existing deep learning methods to a specific dataset.
The paper tackled the problem of recognizing the American Sign Language alphabet from RGB images, achieving an accuracy of 83.29% using a squeezenet architecture optimized for mobile devices.
Tremendous headway has been made in the field of 3D hand pose estimation but the 3D depth cameras are usually inaccessible. We propose a model to recognize American Sign Language alphabet from RGB images. Images for the training were resized and pre-processed before training the Deep Neural Network. The model was trained on a squeezenet architecture to make it capable of running on mobile devices with an accuracy of 83.29%.