Neuromorphic BrailleNet: Accurate and Generalizable Braille Reading Beyond Single Characters through Event-Based Optical Tactile Sensing

2026-01-27

AI Summary

This work proposes a novel approach to continuous braille recognition by introducing a neuromorphic event-based tactile sensor (Evetac), overcoming the inefficiency of character-by-character scanning and the high latency and environmental sensitivity of vision-based methods. Inspired by human finger sliding strategies, the system captures dynamic contact event streams and integrates spatiotemporal segmentation with a lightweight ResNet classifier to achieve high-speed, robust recognition across varying braille layouts and reading speeds. Under standard indentation depth, the system attains character-level accuracy of at least 98% and word-level accuracy exceeding 90%, substantially surpassing the performance limitations of conventional approaches.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Conventional robotic Braille readers typically rely on discrete, character-by-character scanning, limiting reading speed and disrupting natural flow. Vision-based alternatives often require substantial computation, introduce latency, and degrade in real-world conditions. In this work, we present a high accuracy, real-time pipeline for continuous Braille recognition using Evetac, an open-source neuromorphic event-based tactile sensor. Unlike frame-based vision systems, the neuromorphic tactile modality directly encodes dynamic contact events during continuous sliding, closely emulating human finger-scanning strategies. Our approach combines spatiotemporal segmentation with a lightweight ResNet-based classifier to process sparse event streams, enabling robust character recognition across varying indentation depths and scanning speeds. The proposed system achieves near-perfect accuracy (>=98%) at standard depths, generalizes across multiple Braille board layouts, and maintains strong performance under fast scanning. On a physical Braille board containing daily-living vocabulary, the system attains over 90% word-level accuracy, demonstrating robustness to temporal compression effects that challenge conventional methods. These results position neuromorphic tactile sensing as a scalable, low latency solution for robotic Braille reading, with broader implications for tactile perception in assistive and robotic applications.

Problem

• Braille reading
• tactile sensing
• neuromorphic
• real-time recognition
• continuous scanning

Innovation

• neuromorphic tactile sensing
• event-based vision
• continuous Braille recognition
• spatiotemporal segmentation
• real-time tactile perception