Metraipolis › archive › dc_c141c84b0fd7
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model — arXiv:2608.06252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.06252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:37:45.526Z
- SHA-256 of the archived text
03a8f08ca2a367db211644225fa3328b08595779352cd3eff5e5b59f3aa4334a- Stable URL of this page
https://metraipolis.com/documento/dc_c141c84b0fd7
How to cite
Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model — arXiv:2608.06252 — arXiv (en), https://arxiv.org/abs/2608.06252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c141c84b0fd7 (Metraipolis archive dc_c141c84b0fd7, sha256 03a8f08ca2a367db211644225fa3328b08595779352cd3eff5e5b59f3aa4334a)
BibTeX
@misc{dcc141c84b0fd7,
title = {Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model — arXiv:2608.06252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.06252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c141c84b0fd7; sha256 03a8f08ca2a367db211644225fa3328b08595779352cd3eff5e5b59f3aa4334a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL). Automatic BdSL recognition on personal devices could widen access to education and services. Existing systems use controlled-setting datasets without expert verification and heavyweight pretrained backbones unsuited to on-device use. We introduce RSBdSL38, 10,874 expert-validated images spanning all 38 BdSL hand signs, representing the 51 letters of the Bangla alphabet, recorded from real signers at three special-needs schools across Bangladesh. We propose a lightweight attention based convolutional network of 298,470 parameters, built from grouped bottleneck residual blocks, channel and spatial attention, a multi-scale depthwise hand-feature block, dual pooling, and Swish activations. Trained from scratch, it attains 96.37% accuracy (95.72% +- 0.54% over five seeds), within 1.08 percentage points of the best of nine ImageNet-pretrained efficient architectures under an identical protocol, using 8.5 to 68x fewer parameters and 1.3 to 21.7x fewer MACs. Retrained, it reaches 92.95 to 98.33% on six public BdSL benchmarks, 97.04% on a merged corpus, and 76.25% zero-shot on BdSL-38. Removing any architectural stage costs 7.61 to 89.30 points, against at most 3.17 for the training recipe. Grad-CAM with deletion-insertion and weight-randomization checks confirms that predictions follow the signing hand. A signer-independent split holding out 6 of 36 signers yields 85.18%. Quantized to 0.48 MB, it runs at 3.98 ms per image within a 15.5 MB footprint on a commodity smartphone. Together, RSBdSL38 and our from-scratch model turn benchmark accuracy into deployable accessibility at a fraction of pretrained-backbone cost; dataset, code, and models are released. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.06252 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T10:23:31.064Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).