Sweat Gland Enhancement Method for Fingertip OCT Images Based on Generative Adversarial Network

被引：0
作者：
Miao, Qingran [1 ]
Wang, Haixia [2 ]
Zhang, Yilong [2 ]
Yan, Rui [2 ]
Liu, Yipeng [2 ]
机构：
[1] Zhejiang University of Technology, College of Information Engineering, Hangzhou
[2] Zhejiang University of Technology, College of Computer Science and Technology, Hangzhou
来源：
IEEE Transactions on Biometrics, Behavior, and Identity Science | 2024年 / 6卷 / 04期
基金：
中国国家自然科学基金;
关键词：
enhancement; generative adversarial network (GAN); Optical coherence tomography (OCT); paired dataset generation strategy; sweat gland;
D O I：
10.1109/TBIOM.2024.3459812
中图分类号：
学科分类号：
摘要：
Sweat pores are gaining recognition as a secure, reliable, and identifiable third-level fingerprint feature. Challenges arise in collecting sweat pores when fingers are contaminated, dry, or damaged, leading to unclear or vanished surface sweat pores. Optical Coherence Tomography (OCT) has been applied in the collection of fingertip biometric features. The sweat pores mapped from the subcutaneous sweat glands collected by OCT possess higher security and stability. However, speckle noise in OCT images can blur sweat glands making segmentation and extraction difficult. Traditional denoising methods cause unclear sweat gland contours and structural loss due to smearing and excessive smoothing. Deep learning-based methods have not achieved good results due to the lack of clean images as ground-truth. This paper proposes a sweat gland enhancement method for fingertip OCT images based on Generative Adversarial Network (GAN). It can effectively remove speckle noise while eliminating irrelevant structures and repairing the lost structure of sweat glands, ultimately improving the accuracy of sweat gland segmentation and extraction. To the best knowledge, it is the first time that sweat gland enhancement is investigated and proposed. In this method, a paired dataset generation strategy is proposed, which can extend few manually enhanced ground-truth into a high-quality paired dataset. An improved Pix2Pix for sweat gland enhancement is proposed, with the addition of a perceptual loss to mitigate structural distortions during the image translation process. It's worth noting that after obtaining the paired dataset, any advanced supervised image-to-image translation network can be adapted into our framework for enhancement. Experiments are carried out to verify the effectiveness of the proposed method. © 2019 IEEE.
引用
收藏
页码：550 / 560
页数：10
相关论文
共 69 条
  • [11] Ding B., Wang H., Liang R., Zhang Y., Chen P., End-to-end surface and internal fingerprint reconstruction from optical coherence tomography based on contour regression, IEEE Trans. Inf. Forensics Security, 18, pp. 162-176, (2023)
  • [12] Sun S., Guo Z., Sweat glands extraction in optical coherence tomography fingerprints, in Proc. Int. Conf. Secur., Pattern Anal., Cybern. (SPAC), pp. 579-584, (2017)
  • [13] Ding B., Wang H.X., Surface and internal fingerprint reconstruction from optical coherence tomography through convolutional neural network, IEEE Trans. Inf. Forensics Security, 16, pp. 685-700, (2021)
  • [14] Zhang Y., Li X., Wang H., Wang R., Chen P., Liang R., Sweat gland extraction from optical coherence tomography using convolutional neural network, IEEE Trans. Instrum. Meas., 72, pp. 1-16, (2022)
  • [15] Schmitt J.M., Xiang S.H., Yung K.M., Speckle in optical coherence tomography, J. Biomed. Opt., 4, 1, pp. 95-105, (1999)
  • [16] Wang L., Tschudi T., Halldorsson T., Speckle reduction in laser projection systems by diffractive optical elements, Appl. Opt., 37, 10, pp. 1770-1775, (1998)
  • [17] Scott A., Farsiu S., Enyedi L., Wallace D., Toth C., Imaging the infant retina with a hand-held spectral-domain optical coherence tomography device, Amer. J. Ophthalmol., 147, pp. 364-373, (2009)
  • [18] Zhang X., Liu L., Fei Z., Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images, J. Biomed. Opt., 19, 6, (2014)
  • [19] Esmaeili M., Dehnavi M.A., Rabbani H., Speckle noise reduction in optical coherence tomography using two-dimensional curvelet-based dictionary learning, J. Med. Signals Sens., 7, 2, pp. 86-91, (2017)
  • [20] Puvanathasan P., Bizheva K., Interval type-ii fuzzy anisotropic diffusion algorithm for speckle noise reduction in optical coherence tomography images, Opt. Exp., 17, 2, pp. 733-746, (2009)
1234567