American Sign Language Alphabet Recognition using Deep Learning

05/14/2019

∙

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

READ FULL TEXT

American Sign Language Alphabet Recognition using Deep Learning

Learning to Estimate 3D Hand Pose from Single RGB Images

Sign Language Fingerspelling Classification from Depth and Color Images using a Deep Belief Network

Bangla sign language recognition using concatenated BdSL network

DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System

Sign Language Recognition Analysis using Multimodal Data

Despeckling Sentinel-1 GRD images by deep learning and application to narrow river segmentation

Combining Efficient and Precise Sign Language Recognition: Good pose estimation library is all you need

American Sign Language Alphabet Recognition using Deep Learning

Related Research

Learning to Estimate 3D Hand Pose from Single RGB Images

Sign Language Fingerspelling Classification from Depth and Color Images using a Deep Belief Network

Bangla sign language recognition using concatenated BdSL network

DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System

Sign Language Recognition Analysis using Multimodal Data

Despeckling Sentinel-1 GRD images by deep learning and application to narrow river segmentation

Combining Efficient and Precise Sign Language Recognition: Good pose estimation library is all you need