STEMNIST: Spiking Tactile Extended MNIST Neuromorphic Dataset

2026-01-04

arXiv.org

AI Summary

Existing neuromorphic tactile datasets are limited in scale and category, hindering their applicability to complex recognition tasks in real-world scenarios. To address this gap, this work introduces STEMNIST, a large-scale event-driven tactile dataset that extends tactile recognition from digits to 35 alphanumeric characters. It comprises 7,700 samples collected from 34 participants using a 16×16 tactile sensor array sampled at 120 Hz, with over one million spike events generated via adaptive temporal differential encoding. STEMNIST establishes the first tactile benchmark featuring complex characters with rich spatiotemporal structure and spatial variability, bridging the gap between simplified classification tasks and realistic tactile interaction. Baseline experiments demonstrate the dataset’s utility and challenge, with CNN and SNN models achieving 90.91% and 89.16% accuracy, respectively, providing a public, reproducible platform for advancing neuromorphic tactile perception research.

Technology Category

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

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance

Abstract

Tactile sensing is essential for robotic manipulation, prosthetics and assistive technologies, yet neuromorphic tactile datasets remain limited compared to their visual counterparts. We introduce STEMNIST, a large-scale neuromorphic tactile dataset extending ST-MNIST from 10 digits to 35 alphanumeric classes (uppercase letters A--Z and digits 1--9), providing a challenging benchmark for event-based haptic recognition. The dataset comprises 7,700 samples collected from 34 participants using a custom \(16\times 16\) tactile sensor array operating at 120 Hz, encoded as 1,005,592 spike events through adaptive temporal differentiation. Following EMNIST's visual character recognition protocol, STEMNIST addresses the critical gap between simplified digit classification and real-world tactile interaction scenarios requiring alphanumeric discrimination. Baseline experiments using conventional CNNs (90.91% test accuracy) and spiking neural networks (89.16%) establish performance benchmarks. The dataset's event-based format, unrestricted spatial variability and rich temporal structure makes it suitable for testing neuromorphic hardware and bio-inspired learning algorithms. STEMNIST enables reproducible evaluation of tactile recognition systems and provides a foundation for advancing energy-efficient neuromorphic perception in robotics, biomedical engineering and human-machine interfaces. The dataset, documentation and codes are publicly available to accelerate research in neuromorphic tactile computing.

Problem

• neuromorphic tactile dataset
• event-based haptic recognition
• alphanumeric discrimination
• tactile sensing
• spiking neural networks

Innovation

• neuromorphic tactile sensing
• spiking neural networks
• event-based dataset
• adaptive temporal differentiation
• alphanumeric haptic recognition