Real-Time Hand Gesture Classification Using Infrared Sensor Arrays-Based Wearable Bracelet and Efficient 1-D Convolutional Neural Network

Hand gesture recognition is pivotal for intuitive human-machine interaction, particularly in healthcare and assistive technologies where traditional interfaces (e.g., keyboards) are impractical. Existing modalities like electromyography (EMG) and inertial sensors (IMUs) struggle with noise sensitivity, motion dependency, or limited resolution for fine gestures. This work proposes infrared (IR) sensing as a robust alternative, leveraging reflected light patterns to capture both macro and micro gestures without relying on muscle activity or pronounced arm movements. We conducted experiments and compared different architectures to ensure the correct classification of hand gestures with the lowest possible latency, when targeting real-time processing. Experimental results demonstrate that shallow 2-layer 1D CNNs achieve rapid inference (3 ms) and minimal memory (56 kB) but suffer from low accuracy (81.45%), while deeper 12-layer CNNs attain 98.29% accuracy at prohibitive cost (176 ms latency, 17.4 MB memory). A 6-layer 1D CNN strikes an optimal balance, delivering 95.97% accuracy with moderate resources (56 ms latency, 640 kB memory), outperforming similarly accurate LSTM (94.88%, 136 ms) and RNN (96.59%, 102 ms) models. Confusion matrix analysis confirms consistent performance across 7 gestures, including nuanced distinctions like thumb-index vs. thumb-pinky pinches. By optimizing architectural depth and sensor integration, this work enables real-time operation on microcontrollers like the STM32F7, advancing applications in touchless medical interfaces and assistive devices for users with motor impairments.