Spiking Neural Network Model for Hand Gesture Interpretation and Text Output
- Version
- Download 14
- File Size 548.08 KB
- File Count 1
- Create Date 19 March 2026
- Last Updated 19 March 2026
Spiking Neural Network Model for Hand Gesture Interpretation and Text Output
1.Merugu Manish Kumar, 2.Mogili Ravindar, 3.Jagannatham Krishnahitha, 4.Bollaram Shiva, 5.Anasuri Sriya
Department of CSE (Artificial Intelligence & Machine Learning)
Jyothishmathi Institute of Technology and Science, Karimnagar, Telangana, India manishmerugu13@gmail.com,
jagannathamkrishnahitha@gmail.com, shivabollram@gmail.com, anasurisriya@gmail.com
Abstract—This project presents a Spiking Neural Network (SNN)–based system for real-time hand gesture interpretation and textbgeneration. The system uses MediaPipe to extract 21- point hand landmarks from live video input. These features are encoded into spike trains using Time-To First-Spike encoding and processed by an SNN model to recognize both static and dynamic hand gestures. Recognized gestures are converted into meaningful text outputs to support natural human–computer in- teraction and assistive communication. Compared to conventional deep learning approaches, the proposed system is lightweight, energy-efficient, and suitable for real-time execution on resource- constrained devices. The results demonstrate the effectiveness of SNNs for gesture-based communication applications.
Index Terms—Spiking Neural Networks, Hand Gesture Recog- nition, Neuromorphic Computing, MediaPipe, Deep Learning, Text Output
Download