Recent advancements in 3D scanning technologies enable us to acquire the hand geometry represented as a threedimensional point cloud. Providing accurate 3D hand scanning and accurately extracting its biometrics are of crucial importancefor a number of applications in medical sciences, fashion industry, augmented and virtual reality (AR/VR). Traditional methods for hand measurement extraction require manual intervention using a measuring tape, which is time-consuming and highly dependent on the operator{\textquoteright}s expertise. In this paper, we propose, to the best of our knowledge, the first deep neural network for automatic hand measurement extraction from a single 3D scan (H-Net). The proposed network follows an encoder-decoder architecture design, taking a point cloud of the hand as input and outputting the reconstructed hand mesh as well as the corresponding measurement values. In order to train the proposed deep model, a novel synthetic dataset of hands in various shapes and poses and their corresponding measurements is proposed. Experimental results on both synthetic data and real scans captured by Occipital Mark I structure sensor demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed.
Nourbakhsh Kaashki, N, Dai, X, Hu, P & Munteanu, A 2022, Automatic and Fast Extraction of 3D Hand Measurements using a Deep Neural Network. in 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Conference Record - IEEE Instrumentation and Measurement Technology Conference, IEEE, pp. 1-6. https://doi.org/10.1109/I2MTC48687.2022.9806686
Nourbakhsh Kaashki, N., Dai, X., Hu, P., & Munteanu, A. (2022). Automatic and Fast Extraction of 3D Hand Measurements using a Deep Neural Network. In 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) (pp. 1-6). (Conference Record - IEEE Instrumentation and Measurement Technology Conference). IEEE. https://doi.org/10.1109/I2MTC48687.2022.9806686
@inproceedings{ffcc63d90e0e480e9375b616f3732d9c,
title = "Automatic and Fast Extraction of 3D Hand Measurements using a Deep Neural Network",
abstract = "Recent advancements in 3D scanning technologies enable us to acquire the hand geometry represented as a threedimensional point cloud. Providing accurate 3D hand scanning and accurately extracting its biometrics are of crucial importancefor a number of applications in medical sciences, fashion industry, augmented and virtual reality (AR/VR). Traditional methods for hand measurement extraction require manual intervention using a measuring tape, which is time-consuming and highly dependent on the operator{\textquoteright}s expertise. In this paper, we propose, to the best of our knowledge, the first deep neural network for automatic hand measurement extraction from a single 3D scan (H-Net). The proposed network follows an encoder-decoder architecture design, taking a point cloud of the hand as input and outputting the reconstructed hand mesh as well as the corresponding measurement values. In order to train the proposed deep model, a novel synthetic dataset of hands in various shapes and poses and their corresponding measurements is proposed. Experimental results on both synthetic data and real scans captured by Occipital Mark I structure sensor demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and speed.",
author = "{Nourbakhsh Kaashki}, Nastaran and Xinxin Dai and Pengpeng Hu and Adrian Munteanu",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.",
year = "2022",
month = may,
day = "16",
doi = "10.1109/I2MTC48687.2022.9806686",
language = "English",
isbn = "978-1-6654-8361-2",
series = "Conference Record - IEEE Instrumentation and Measurement Technology Conference",
publisher = "IEEE",
pages = "1--6",
booktitle = "2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)",
}