Neuromorphic visual attention for Sign-language recognition on SpiNNaker
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915989092827136 |
|---|---|
| author | Liskova, Sarka Vedmedenko, Olha Fatahi, Mazdak Hoffmann, Matej Furlong, P. Michael Angelo, Giulia D |
| author_facet | Liskova, Sarka Vedmedenko, Olha Fatahi, Mazdak Hoffmann, Matej Furlong, P. Michael Angelo, Giulia D |
| contents | Sign-language recognition has achieved substantial gains in classification accuracy in recent years; however, the latency and power requirements of most existing methods limit their suitability for real-time deployment. Neuromorphic sensing and processing offer an alternative paradigm based on sparse, event-driven computation that supports low-latency and energy-efficient perception. In this work, we introduce an end-to-end neuromorphic architecture for American Sign Language (ASL) fingerspelling recognition that integrates a spiking visual attention mechanism for online region-of-interest extraction with a compact spiking neural network deployed on the SpiNNaker neuromorphic platform. We benchmark the proposed system against two datasets: a synthetically generated event-based version of the Sign Language MNIST dataset and a natively recorded ASL-DVS dataset, whilst providing a comprehensive overview of Sign-language recognition and related work. This work yields competitive performance in simulation (92.27%) and comparable performance on neuromorphic hardware deployment (83.1%), while achieving the most energy-efficient architecture (0.565 mW) and low latency (3 ms) across all benchmarked approaches. Despite its compact design, the system demonstrates the suitability of task-dependent visual attention applications for edge deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06005 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Neuromorphic visual attention for Sign-language recognition on SpiNNaker Liskova, Sarka Vedmedenko, Olha Fatahi, Mazdak Hoffmann, Matej Furlong, P. Michael Angelo, Giulia D Computer Vision and Pattern Recognition Sign-language recognition has achieved substantial gains in classification accuracy in recent years; however, the latency and power requirements of most existing methods limit their suitability for real-time deployment. Neuromorphic sensing and processing offer an alternative paradigm based on sparse, event-driven computation that supports low-latency and energy-efficient perception. In this work, we introduce an end-to-end neuromorphic architecture for American Sign Language (ASL) fingerspelling recognition that integrates a spiking visual attention mechanism for online region-of-interest extraction with a compact spiking neural network deployed on the SpiNNaker neuromorphic platform. We benchmark the proposed system against two datasets: a synthetically generated event-based version of the Sign Language MNIST dataset and a natively recorded ASL-DVS dataset, whilst providing a comprehensive overview of Sign-language recognition and related work. This work yields competitive performance in simulation (92.27%) and comparable performance on neuromorphic hardware deployment (83.1%), while achieving the most energy-efficient architecture (0.565 mW) and low latency (3 ms) across all benchmarked approaches. Despite its compact design, the system demonstrates the suitability of task-dependent visual attention applications for edge deployment. |
| title | Neuromorphic visual attention for Sign-language recognition on SpiNNaker |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.06005 |