Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network
This work addresses noise removal in optical fringe patterns for applications like interferometry, but it is incremental as it builds on existing deep learning and denoising approaches.
The authors tackled the problem of speckle noise in optical fringe patterns by proposing a deep learning-based filtering method called FPD-CNN, which achieved competitive performance with state-of-the-art denoising techniques while efficiently preserving fringe features at a fast speed.
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.