DeepDensity: Convolutional neural network based estimation of local fringe pattern density. (October 2021)

• Record Type: Journal Article
• Authors: Cywińska, Maria; Brzeski, Filip; Krajnik, Wiktor; Patorski, Krzysztof; Zuo, Chao; Trusiak, Maciej
• Is Part Of: Optics and lasers in engineering. Volume 145(2021)
• Publication Date: 2021-10
• Subjects: Phase measurements -- Local fringe density map -- Convolutional neural network -- Supervised learning -- Full-field optical measurements -- Spatially self-similar patterns; Lasers in engineering -- Periodicals; Optical measurements -- Periodicals; Optics -- Periodicals; Lasers en ingénierie -- Périodiques; Mesures optiques -- Périodiques; Optique -- Périodiques; 621.36605
• DOI: 10.1016/j.optlaseng.2021.106675
• Languages: English
• ISSNs: 0143-8166

Abstract

Highlights: New technique for local fringe density map estimation is proposed. Novel, interesting application for convolutional neural networks in fringe pattern-based measurements is presented. Correct results were obtained for a very small simulated training dataset due to the nature of the analyzed data (fringe patterns described by a spatially self-similar cosine function). The versatility of the developed solution was confirmed by experimental data (even though the training dataset consisted only of simulated data). Abstract: Fringe pattern based measurement techniques are crucial both in macroscale, e.g., fringe projection profilometry, and microscale, e.g., label-free quantitative phase microscopy. Accurate estimation of the local fringe density map can significantly facilitate almost all stages of fringe pattern analysis process. Example includes: (1) using density map as a determinant for the selection of the proper window size in windowed Fourier transform method, (2) guiding the decomposition process in empirical mode decomposition, (3) improving the phase unwrapping accuracy by providing additional reliability indicators, (4) guiding phase estimation process in regularized phase tracking. For these reasons, the accurate and robust estimation of local fringe density map is of high importance and can boost fringe pattern analysis on different stages of processing path, resulting in increased capacity of the full-field noncontact/noninvasive optical measurement system. In this paper, we propose a new, accurate, robust, and fast numerical solution for local fringe density map estimation called DeepDensity. DeepDensity is based on the convolutional neural network and deep learning, making it significantly outperform other conventional solutions to this problem. Numerical simulations and experimental results corroborate the effectiveness of the proposed DeepDensity.