American Sign Language Alphabet Recognition using Deep Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kasukurthi, Nikhil, Rokad, Brij, Bidani, Shiv, Dennisan, Aju
Format: Preprint
Veröffentlicht: 2019
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929485117390848
author Kasukurthi, Nikhil
Rokad, Brij
Bidani, Shiv
Dennisan, Aju
author_facet Kasukurthi, Nikhil
Rokad, Brij
Bidani, Shiv
Dennisan, Aju
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_1905_05487
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle American Sign Language Alphabet Recognition using Deep Learning
Kasukurthi, Nikhil
Rokad, Brij
Bidani, Shiv
Dennisan, Aju
Computer Vision and Pattern Recognition
Artificial Intelligence
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%.
title American Sign Language Alphabet Recognition using Deep Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/1905.05487