Intelligent Ghanaian Sign Language translation: Assessing the effectiveness of deep learning models in bridging the communication gap between hearing non-signers and the deaf in Ghana
dc.contributor.author | Arthur, Lynda Rita | |
dc.date.accessioned | 2024-09-04T09:54:14Z | |
dc.date.available | 2024-09-04T09:54:14Z | |
dc.date.issued | 2023-05 | |
dc.description | Undergraduate thesis submitted to the Department of Computer Science and Information Systems, Ashesi University, in partial fulfillment of Bachelor of Science degree in Management Information Systems, May 2023 | |
dc.description.abstract | The communication gap between the hearing non-signers and the deaf and hard-of-hearing (DHH) in Ghana has been a persistent issue that hinders effective communication and interaction between these groups. This thesis explores the potential of deep learning models in bridging this gap by assessing their effectiveness in accurately translating Ghanaian Sign Language (GhSL) in real time. The research question is, "How accurately can Ghanaian Sign Language be translated in real-time?" The contributions to the field of GhSL recognition include: - Contribution 1: This research adds to the limited exploration of leveraging deep learning for GhSL recognition [27]. - Contribution 2: It prioritises dynamic GhSL signs, as well as double-hand gestures while attaining high accuracy. - Contribution 3: This research provides information on the accuracy score of the predicted signs per real-time translation. Overall, the findings demonstrate the potential of deep learning models in bridging the communication between hearing non-signers and the DHH in Ghana due to its accuracy score of 93.333% and accuracy per real-time prediction ranging from 75.2017% for the sign "Thanks" to 99.9997% for the sign "Hello". The contributions to the field provide a foundation for future research in this area and have practical implications for improving communication and accessibility for the deaf community in Ghana. | |
dc.description.sponsorship | Ashesi University | |
dc.identifier.uri | https://hdl.handle.net/20.500.11988/1137 | |
dc.language.iso | en | |
dc.title | Intelligent Ghanaian Sign Language translation: Assessing the effectiveness of deep learning models in bridging the communication gap between hearing non-signers and the deaf in Ghana | |
dc.type | Undergraduate thesis | en |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Arthur_Lynda_2023_MIS_Thesis.pdf
- Size:
- 8.27 MB
- Format:
- Adobe Portable Document Format