This paper addresses a critical flaw in MediaPipe Holistic's hand Region of Interest (ROI) prediction, which struggles with non-ideal hand orientations, affecting sign language recognition accuracy. We propose a data-driven approach to enhance ROI estimation, leveraging an enriched feature set including additional hand keypoints and the z-dimension. Our results demonstrate better estimates, with higher Intersection-over-Union compared to the current method. Our code and optimizations are available at https://github.com/sign-language-processing/mediapipe-hand-crop-fix.
Cite
@article{arxiv.2405.03545,
title = {Optimizing Hand Region Detection in MediaPipe Holistic Full-Body Pose Estimation to Improve Accuracy and Avoid Downstream Errors},
author = {Amit Moryossef},
journal= {arXiv preprint arXiv:2405.03545},
year = {2024}
}