期刊
IEEE SENSORS JOURNAL
卷 21, 期 4, 页码 4900-4907出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2020.3030321
关键词
Image reconstruction; Inverse problems; Loss measurement; Imaging; Sensors; Deep learning; Permittivity; Inverse scattering; convolutional neural network; structural similarity loss
资金
- National Natural Science Foundation of China [61922075, 41901350]
- Provincial Natural Science Foundation of Anhui [2008085QF285]
- Fundamental Research Funds for the Central Universities [JZ2019HGBZ0151]
This article introduces a structural similarity (SSIM) loss function combined with a mean squared error (MSE) loss function for reconstructing dielectric targets in a DL-IS framework. Numerical tests show that this new perceptually-inspired loss function can effectively enhance imaging quality and model generalization capability.
Deep learning based inverse scattering (DL-IS) methods attract much attention in recent years due to advantages of fast speed and high-quality reconstruction. The loss functions of neural networks in DL-IS methods are commonly based on a pixel-wise mean squared error (MSE) between the reconstructed image and its reference one. In this article, we introduce a structural similarity (SSIM) loss function to combine with the MSE loss for reconstructing dielectric targets under a DL-IS framework. The SSIM loss imposes a further regularization on the target at the perceptual level. Numerical tests for both synthetic and experimental data verify that this new perceptually-inspired loss function can effectively improve the imaging quality and the generalization capability of the trained model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据