ISLR101: An Iranian Word-Level Sign Language Recognition Dataset
Sign language recognition involves modeling complex multichannel information, such as hand shapes and movements, while relying on sufficient sign language-specific data. However, sign languages are often under-resourced, posing a significant challenge for research and development in this field. To a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11015977/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849471033928581120 |
|---|---|
| author | Hossein Ranjbar Alireza Taheri |
| author_facet | Hossein Ranjbar Alireza Taheri |
| author_sort | Hossein Ranjbar |
| collection | DOAJ |
| description | Sign language recognition involves modeling complex multichannel information, such as hand shapes and movements, while relying on sufficient sign language-specific data. However, sign languages are often under-resourced, posing a significant challenge for research and development in this field. To address this gap, we introduce ISLR101, the first publicly available Iranian Sign Language dataset for isolated sign language recognition. This comprehensive dataset includes 4,614 videos covering 101 distinct signs, recorded from 10 different signers (3 deaf individuals, 2 sign language interpreters, and 5 L2 learners) against varied backgrounds, with a resolution of <inline-formula> <tex-math notation="LaTeX">$800\times 600$ </tex-math></inline-formula> pixels and a frame rate of 25 frames per second. It also includes skeleton pose information extracted using OpenPose. We establish both a visual appearance-based and a skeleton-based framework as baseline models, thoroughly training and evaluating them on ISLR101. These models achieve 97.01% and 94.02% accuracy on the test set, respectively. Additionally, we publish the train, validation, and test splits to facilitate fair comparisons. |
| format | Article |
| id | doaj-art-33cc32b094d44022be7b651206a532f9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-33cc32b094d44022be7b651206a532f92025-08-20T03:24:59ZengIEEEIEEE Access2169-35362025-01-0113961479615810.1109/ACCESS.2025.357407411015977ISLR101: An Iranian Word-Level Sign Language Recognition DatasetHossein Ranjbar0https://orcid.org/0009-0001-5396-1206Alireza Taheri1https://orcid.org/0000-0001-5826-260XMechanical Engineering Department, Social and Cognitive Robotics Laboratory, Sharif University of Technology, Tehran, IranMechanical Engineering Department, Social and Cognitive Robotics Laboratory, Sharif University of Technology, Tehran, IranSign language recognition involves modeling complex multichannel information, such as hand shapes and movements, while relying on sufficient sign language-specific data. However, sign languages are often under-resourced, posing a significant challenge for research and development in this field. To address this gap, we introduce ISLR101, the first publicly available Iranian Sign Language dataset for isolated sign language recognition. This comprehensive dataset includes 4,614 videos covering 101 distinct signs, recorded from 10 different signers (3 deaf individuals, 2 sign language interpreters, and 5 L2 learners) against varied backgrounds, with a resolution of <inline-formula> <tex-math notation="LaTeX">$800\times 600$ </tex-math></inline-formula> pixels and a frame rate of 25 frames per second. It also includes skeleton pose information extracted using OpenPose. We establish both a visual appearance-based and a skeleton-based framework as baseline models, thoroughly training and evaluating them on ISLR101. These models achieve 97.01% and 94.02% accuracy on the test set, respectively. Additionally, we publish the train, validation, and test splits to facilitate fair comparisons.https://ieeexplore.ieee.org/document/11015977/Sign languagesign language recognitiontransformersdataset |
| spellingShingle | Hossein Ranjbar Alireza Taheri ISLR101: An Iranian Word-Level Sign Language Recognition Dataset IEEE Access Sign language sign language recognition transformers dataset |
| title | ISLR101: An Iranian Word-Level Sign Language Recognition Dataset |
| title_full | ISLR101: An Iranian Word-Level Sign Language Recognition Dataset |
| title_fullStr | ISLR101: An Iranian Word-Level Sign Language Recognition Dataset |
| title_full_unstemmed | ISLR101: An Iranian Word-Level Sign Language Recognition Dataset |
| title_short | ISLR101: An Iranian Word-Level Sign Language Recognition Dataset |
| title_sort | islr101 an iranian word level sign language recognition dataset |
| topic | Sign language sign language recognition transformers dataset |
| url | https://ieeexplore.ieee.org/document/11015977/ |
| work_keys_str_mv | AT hosseinranjbar islr101aniranianwordlevelsignlanguagerecognitiondataset AT alirezataheri islr101aniranianwordlevelsignlanguagerecognitiondataset |