期刊
OPTICS AND LASERS IN ENGINEERING
卷 126, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.optlaseng.2019.105853
关键词
Fringe patterns denoising; Image restoration; Regularization; Convolution neural network; Leaky relu
类别
资金
- National Natural Science Foundation of China [61671276, 11971269]
- Natural Science Foundation of Shandong Province of China [ZR2019MF045]
- Teaching Reform and Research Project of School of Mathematics of Shandong University
Optical fringe patterns are often contaminated by speckle noise, making it difficult to accurately and robustly extract their phase fields. To deal with this problem, we propose a filtering method based on deep learning, called optical fringe patterns denoising convolutional neural network (FPD-CNN), for directly removing speckle from the input noisy fringe patterns. Regularization technology is integrated into the design of deep architecture. Specifically, the FPD-CNN method is divided into multiple stages, each stage consists of a set of convolutional layers along with batch normalization and leaky rectified linear unit (Leaky ReLU) activation function. The end-to-end joint training is carried out using the Euclidean loss. Extensive experiments on simulated and experimental optical fringe patterns, especially finer ones with high-density regions, show that the proposed method is competitive with some state-of-the-art denoising techniques in spatial or transform domains, efficiently preserving main features of fringe at a fairly fast speed.
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