标题：Optical fringe patterns filtering based on multi-stage convolution neural network
作者：Lin, Bowen; Fu, Shujun; Zhang, Caiming; Wang, Fengling; Li, Yuliang
作者机构：[Lin, Bowen; Fu, Shujun] Shandong Univ, Sch Math, Jinan 250100, Shandong, Peoples R China.; [Wang, Fengling] Shandong Univ Arts, Coll Arts Managemen 更多
通讯作者：Fu, Shujun;Fu, SJ
通讯作者地址：[Fu, SJ]Shandong Univ, Sch Math, Jinan 250100, Shandong, Peoples R China.
来源：OPTICS AND LASERS IN ENGINEERING
关键词：Fringe patterns denoising; Image restoration; Regularization;; Convolution neural network; Leaky relu
摘要：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.