Investigating Motion History Images and Convolutional Neural Networks for Isolated Irish Sign Language Fingerspelling Recognition

The limited global competency in sign language makes the objective of improving communication for the deaf and hard-of-hearing community through computational processing both vital and necessary. In an effort to address this problem, our research leverages the Irish Sign Language hand shape (ISL-HS) dataset and state-of-the-art deep learning architectures to recognize the Irish Sign Language alphabet. We streamline the feature extraction methodology and pave the way for the efficient use of Convolutional Neural Networks (CNNs) by using Motion History Images (MHIs) for monitoring the sign language motions. The effectiveness of numerous powerful CNN architectures in deciphering the intricate patterns of motion captured in MHIs is investigated in this research. The process includes generating MHIs from the ISL dataset and then using these images to train several CNN neural network models and evaluate their ability to recognize the Irish Sign Language alphabet. The results demonstrate the possibility of investigating MHIs with advanced CNNs to enhance sign language recognition, with a noteworthy accuracy percentage. By contributing to the development of language processing tools and technologies for Irish Sign Language, this research has the potential to address the lack of technological communicative accessibility and inclusion for the deaf and hard-of-hearing community in Ireland.