Date of Award

4-19-2024

Document Type

Honors Thesis

Department

Engineering & Computer Science

First Advisor

Ackley Will

Abstract

Several machine learning researchers have developed algorithms recognizing American Sign Language (ASL), but few have applied the algorithms to real-world situations, such as with portable ASL learning applications. This project develops a beta version of a mobile application designed to allow beginner ASL learners to practice basic ASL vocabulary and receive feedback about their signing accuracy. Building on Dongxu Li et al.’s I3D sign language recognition algorithm and 2000-word dataset, the app seeks to determine whether the I3D algorithm can sufficiently recognize a user’s motions when recorded from a mobile device and accurately classify whether or not the user signed correctly. My repository for the machine learning portion of this project, forked from Li et al.’s WLASL repository, is available at https://qithub.com/sandrineadap/WLASLR-cloned, and a video to demonstrate the progress of the mobile app can be found in the repository’s README file.

Subject Area

Computer vision, Machine learning, Mobile apps, American Sign Language

Download

Files over 3MB may be slow to open. For best results, right-click and select "save as..."

Share

COinS