loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Masakazu Fujio 1 ; Keiichiro Nakazaki 2 ; Naoto Miura 2 ; Yosuke Kaga 1 and Kenta Takahashi 1

Affiliations: 1 Research and Development Group Hitachi, Ltd., Yokohama, Kanagawa, Japan ; 2 Research and Development Group Hitachi, Ltd., Kokubunji, Tokyo, Japan

Keyword(s): Bezier Curve, Semantic Segmentation, Shape-Aware Method, Finger Region Segmentationsed.

Abstract: This paper presents a shape-aware finger region segmentation method from hand images for user authentication. The recent development of encoder-decoder network-based deep learning technologies dramatically improved image segmentation accuracy. Although those methods predict the probability of belonging to each object pixel by pixel, it is impossible to consider whether the estimated region has a finger-like shape. We adopted a deep learning-based Bezier curve estimation method to realize shape-aware model training. We improved the accuracy with the case of warm color, complex background, and finger touching that would be difficult to estimate target regions using color-based heuristics or traditional pixel-by-pixel methods. We prepared ground truth data for each finger region (index finger, middle finger, ring finger, little finger), then trained both the conventional pixel-by-pixel estimation method and our Bezier curve estimation methods. Quantitative results showed that the propos ed models outperform traditional methods (pixel-wise IOU 0.935) and practical speed. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.142.201.91

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Fujio, M.; Nakazaki, K.; Miura, N.; Kaga, Y. and Takahashi, K. (2023). Finger Region Estimation by Boundary Curve Modeling and Bezier Curve Learning. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-626-2; ISSN 2184-4313, SciTePress, pages 371-378. DOI: 10.5220/0011684400003411

@conference{icpram23,
author={Masakazu Fujio. and Keiichiro Nakazaki. and Naoto Miura. and Yosuke Kaga. and Kenta Takahashi.},
title={Finger Region Estimation by Boundary Curve Modeling and Bezier Curve Learning},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2023},
pages={371-378},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011684400003411},
isbn={978-989-758-626-2},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Finger Region Estimation by Boundary Curve Modeling and Bezier Curve Learning
SN - 978-989-758-626-2
IS - 2184-4313
AU - Fujio, M.
AU - Nakazaki, K.
AU - Miura, N.
AU - Kaga, Y.
AU - Takahashi, K.
PY - 2023
SP - 371
EP - 378
DO - 10.5220/0011684400003411
PB - SciTePress