Skip to main navigation Skip to search Skip to main content

Utilising transformers for American Sign Language fingerspelling recognition

    Research output: Chapter in Book/Report/Conference proceedingChapter

    Abstract

    This paper presents a machine learning approach to American Sign Language (ASL) fingerspelling recognition using Transformer models. Addressing the challenges of high variability in hand shapes, movement, and signing speed, the study utilises the new ASL Fingerspelling Recognition Corpus and the CRISP-DM methodology to develop and evaluate a proof-of-concept model. The model achieved a mean Levenshtein distance of 4.7, corresponding to an error rate of 16.37%. This research demonstrates the feasibility of using advanced AI techniques to enhance accessibility for the deaf and hard of hearing communities by translating ASL fingerspelling into text.
    Original languageEnglish
    Title of host publication2024 IEEE 24th International Symposium on Computational Intelligence and Informatics (CINTI)
    PublisherIEEE
    Pages000129-000134
    ISBN (Print)9798350353433
    DOIs
    Publication statusPublished - 19 Nov 2024

    Keywords

    • AI accessibility
    • American Sign Language (ASL)
    • CRISP-DM
    • Deaf and hard of hearing
    • Fingerspelling recognition
    • Levenshtein distance
    • Machine learning
    • MediaPipe
    • PyTorch
    • Transformer models

    Fingerprint

    Dive into the research topics of 'Utilising transformers for American Sign Language fingerspelling recognition'. Together they form a unique fingerprint.

    Cite this