Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition

TL;DR

This paper evaluates deep learning methods for pose estimation in sign language recognition, introduces a new dataset, and demonstrates that transfer learning enhances accuracy, providing a baseline for future research.

Contribution

Introduces a new dataset for pose estimation in sign language recognition and evaluates deep learning methods, highlighting the benefits of transfer learning.

Findings

Transfer learning improves pose estimation accuracy.

Deep learning methods perform well on the new dataset.

The dataset serves as a baseline for future research.

Abstract

Human body pose estimation and hand detection are two important tasks for systems that perform computer vision-based sign language recognition(SLR). However, both tasks are challenging, especially when the input is color videos, with no depth information. Many algorithms have been proposed in the literature for these tasks, and some of the most successful recent algorithms are based on deep learning. In this paper, we introduce a dataset for human pose estimation for SLR domain. We evaluate the performance of two deep learning based pose estimation methods, by performing user-independent experiments on our dataset. We also perform transfer learning, and we obtain results that demonstrate that transfer learning can improve pose estimation accuracy. The dataset and results from these methods can create a useful baseline for future works.