ABSTRACT
We propose a new framework for processing fringe patterns (FPs). Our novel, to the best of our knowledge, approach builds upon the hypothesis that the denoising and normalization of FPs can be learned by a deep neural network if enough pairs of corrupted and ideal FPs are provided. The main contributions of this paper are the following: (1) we propose the use of the U-net neural network architecture for FP normalization tasks; (2) we propose a modification for the distribution of weights in the U-net, called here the V-net model, which is more convenient for reconstruction tasks, and we conduct extensive experimental evidence in which the V-net produces high-quality results for FP filtering and normalization; (3) we also propose two modifications of the V-net scheme, namely, a residual version called ResV-net and a fast operating version of the V-net, to evaluate potential improvements when modifying our proposal. We evaluate the performance of our methods in various scenarios: FPs corrupted with different degrees of noise, and corrupted with different noise distributions. We compare our methodology versus other state-of-the-art methods. The experimental results (on both synthetic and real data) demonstrate the capabilities and potential of this new paradigm for processing interferograms.
