- Title
- Investigating signer-independent sign language recognition on the lsa64 dataset
- Creator
- Marais, Marc
- Creator
- Brown, Dane L
- Creator
- Connan, James
- Creator
- Boby, Alden
- Creator
- Kuhlane, Luxolo L
- Subject
- To be catalogued
- Date Issued
- 2022
- Date
- 2022
- Type
- text
- Type
- article
- Identifier
- http://hdl.handle.net/10962/465179
- Identifier
- vital:76580
- Identifier
- xlink:href="https://www.researchgate.net/profile/Marc-Marais/publication/363174384_Investigating_Signer-Independ-ent_Sign_Language_Recognition_on_the_LSA64_Dataset/links/63108c7d5eed5e4bd138680f/Investigating-Signer-Independent-Sign-Language-Recognition-on-the-LSA64-Dataset.pdf"
- Description
- Conversing with hearing disabled people is a significant challenge; however, computer vision advancements have significantly improved this through automated sign language recognition. One of the common issues in sign language recognition is signer-dependence, where variations arise from varying signers, who gesticulate naturally. Utilising the LSA64 dataset, a small scale Argentinian isolated sign language recognition, we investigate signer-independent sign language recognition. An InceptionV3-GRU architecture is employed to extract and classify spatial and temporal information for automated sign language recognition. The signer-dependent approach yielded an accuracy of 97.03%, whereas the signer-independent approach achieved an accuracy of 74.22%. The signer-independent system shows promise towards addressing the real-world and common issue of signer-dependence in sign language recognition.
- Format
- computer
- Format
- online resource
- Format
- application/pdf
- Format
- 1 online resource (6 pages)
- Format
- Publisher
- Southern Africa Telecommunication Networks and Applications Conference (SA TNAC)
- Language
- English
- Relation
- Southern Africa Telecommunication Networks and Applications Conference (SA TNAC)
- Relation
- Marais, M., Brown, D., Connan, J., Boby, A. and Kuhlane, L.L., 2022. Investigating signer-independent sign language recognition on the lsa64 dataset. In Southern Africa Telecommunication Networks and Applications Conference (SA TNAC)
- Relation
- Southern Africa Telecommunication Networks and Applications Conference (SA TNAC) 2022
- Rights
- Publisher
- Rights
- Use of this resource is governed by the terms and conditions of Southern Africa Telecommunication Networks and Applications Conference (SA TNAC) Statement (https://www.satnac.org.za/)
- Rights
- Closed Access
- Hits: 86
- Visitors: 84
- Downloads: 3
Collections
RU Department of Computer Science
SDG 09. Industry, Innovation and Infrastructure
Brown, Dane A (Associate Prof)
Connan, James (Mr)
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE1 | Investigating signer-independent sign language recognition on the lsa64 dataset.pdf | 680 KB | Adobe Acrobat PDF | View Details Download |