Super-resolution algorithm for the characterization of sweat glands in fingerprint OCT images

Zhiyu Song; Yongping Lin; Liu Xiong; Zhifang Li

doi:10.1364/JOSAA.503212

Journal of the Optical Society of America A
Vol. 40,
Issue 11,
pp. 2068-2077
(2023)
•https://doi.org/10.1364/JOSAA.503212

Super-resolution algorithm for the characterization of sweat glands in fingerprint OCT images

Zhiyu Song, Yongping Lin, Liu Xiong, and Zhifang Li

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Zhiyu Song, Yongping Lin, Liu Xiong, and Zhifang Li, "Super-resolution algorithm for the characterization of sweat glands in fingerprint OCT images," J. Opt. Soc. Am. A 40, 2068-2077 (2023)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Related Topics
Table of Contents Category
- Image Processing and Image Analysis
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: August 22, 2023
- Revised Manuscript: October 6, 2023
- Manuscript Accepted: October 7, 2023
- Published: October 24, 2023

Abstract

Optical coherence tomography (OCT) is a noninvasive optical imaging technique that can be used to produce three-dimensional images of fingerprints. However, the low quality and poor resolution of the regions of interest (ROIs) in OCT images make it challenging to segment small tissues accurately. To address this issue, a super-resolution (SR) network called ESRNet has been developed to enhance the quality of OCT images, facilitating their applications in research. Firstly, the performance of the SR images produced by ESRNet is evaluated by comparing it to those generated by five other SR methods. Specifically, the SR performance is evaluated using three upscale factors ($2 \times$, $3 \times$, and $4 \times$) to assess the quality of the enhanced images. Based on the results obtained from the three datasets, it is evident that ESRNet outperforms current advanced networks in terms of SR performance. Furthermore, the segmentation accuracy of sweat glands has been significantly improved by the SR images. The number of sweat glands in the top view increased from 102 to 117, further substantiating the performance of the ESRNet network. The spiral structure of sweat glands is clear to human eyes and has been verified by showing similar left–right-handed spiral numbers. Finally, a sweat gland recognition method for the SR 3D images is proposed.

Full Article | PDF Article

More Like This

Automatic algorithm for the characterization of sweat ducts in a three-dimensional fingerprint

Chuiyu Kong, Dezi Li, Yongping Lin, and Zhifang li
Opt. Express 29(19) 30706-30714 (2021)

Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network

Xueshen Li, Zhenxing Dong, Hongshan Liu, Jennifer J. Kang-Mieler, Yuye Ling, and Yu Gan
Biomed. Opt. Express 14(10) 5148-5161 (2023)

Self super-resolution of optical coherence tomography images based on deep learning

Zhuoqun Yuan, Di Yang, Weike Wang, Jingzhu Zhao, and Yanmei Liang
Opt. Express 31(17) 27566-27581 (2023)

Previous Article Next Article

Data availability

The private data presented in this study are available upon request from the corresponding author. The details of the public datasets are as follows: The Eye OCT Dataset is available at [46]. The OCT2017 Dataset is available at [47]. The code is made publicly available at [48].

46. https://tianchi.aliyun.com/dataset/90672?t=1695632341415.

47. P. Mooney, “Retinal OCT Images,” Kaggle (2018), https://www.kaggle.com/datasets/paultimothymooney/kermany2018.

48. Y. Lin, “ESRNet,” GitHub (2023), https://github.com/Ancera111/ESRNet.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (8)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (3)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (3)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

		Eye OCT Dataset		OCT2017 Dataset		Self-Made Fingerprint Dataset
		PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
Bigjpg	$2 \times$	38.001	0.995	36.577	0.977	30.397	0.986
SRCNN	$2 \times$	33.666	0.934	30.413	0.859	31.739	0.938
	$3 \times$	31.986	0.912	29.902	0.742	31.940	0.933
	$4 \times$	31.010	0.890	26.589	0.663	32.561	0.933
FSRCNN	$2 \times$	33.926	0.936	30.467	0.861	30.495	0.935
	$3 \times$	31.865	0.911	27.894	0.739	30.458	0.920
	$4 \times$	30.997	0.857	26.747	0.666	30.734	0.909
ESPCN	$2 \times$	37.409	0.823	35.779	0.951	10.963	0.909
	$3 \times$	20.827	0.831	18.604	0.692	31.536	0.937
	$4 \times$	38.947	0.932	37.751	0.973	32.130	0.949
SRResNet	$2 \times$	39.839	0.951	39.839	0.951	33.031	0.982
	$3 \times$	29.404	0.942	28.361	0.766	29.775	0.892
	$4 \times$	39.839	0.951	39.839	0.951	33.498	0.970
ESRNet (ours)	$2 \times$	39.839	0.951	39.839	0.951	35.998	0.959
	$3 \times$	31.078	0.958	30.307	0.832	30.516	0.889
	$4 \times$	39.839	0.951	39.839	0.951	29.633	0.914

	Original	SR
mIOU	74.82	78.52
mPA	82.83	83.57
Number	102.00	117.00

		Eye OCT Dataset		OCT2017 Dataset		Self-Made Fingerprint Dataset
		PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
Bigjpg	$2 \times$	38.001	0.995	36.577	0.977	30.397	0.986
SRCNN	$2 \times$	33.666	0.934	30.413	0.859	31.739	0.938
	$3 \times$	31.986	0.912	29.902	0.742	31.940	0.933
	$4 \times$	31.010	0.890	26.589	0.663	32.561	0.933
FSRCNN	$2 \times$	33.926	0.936	30.467	0.861	30.495	0.935
	$3 \times$	31.865	0.911	27.894	0.739	30.458	0.920
	$4 \times$	30.997	0.857	26.747	0.666	30.734	0.909
ESPCN	$2 \times$	37.409	0.823	35.779	0.951	10.963	0.909
	$3 \times$	20.827	0.831	18.604	0.692	31.536	0.937
	$4 \times$	38.947	0.932	37.751	0.973	32.130	0.949
SRResNet	$2 \times$	39.839	0.951	39.839	0.951	33.031	0.982
	$3 \times$	29.404	0.942	28.361	0.766	29.775	0.892
	$4 \times$	39.839	0.951	39.839	0.951	33.498	0.970
ESRNet (ours)	$2 \times$	39.839	0.951	39.839	0.951	35.998	0.959
	$3 \times$	31.078	0.958	30.307	0.832	30.516	0.889
	$4 \times$	39.839	0.951	39.839	0.951	29.633	0.914

	Original	SR
mIOU	74.82	78.52
mPA	82.83	83.57
Number	102.00	117.00

Abstract

Data availability

Cited By

Figures (8)

Tables (3)

Equations (3)

Journal of the Optical Society of America A