Real-time Sign Language Fingerspelling Recognition using Convolutional Neural Networks from Depth map

TL;DR

This paper presents a real-time CNN-based system for sign language fingerspelling recognition from depth maps, achieving high accuracy and speed, and demonstrating improved generalization with diverse training data.

Contribution

The work introduces a CNN approach for recognizing 31 sign language symbols from depth data, with the highest reported accuracy and real-time processing speed.

Findings

99.99% accuracy for observed signers

83.58% to 85.49% accuracy for new signers

3 ms processing time per image

Abstract

Sign language recognition is important for natural and convenient communication between deaf community and hearing majority. We take the highly efficient initial step of automatic fingerspelling recognition system using convolutional neural networks (CNNs) from depth maps. In this work, we consider relatively larger number of classes compared with the previous literature. We train CNNs for the classification of 31 alphabets and numbers using a subset of collected depth data from multiple subjects. While using different learning configurations, such as hyper-parameter selection with and without validation, we achieve 99.99% accuracy for observed signers and 83.58% to 85.49% accuracy for new signers. The result shows that accuracy improves as we include more data from different subjects during training. The processing time is 3 ms for the prediction of a single image. To the best of our knowledge, the system achieves the highest accuracy and speed. The trained model and dataset is available on our repository.