Deep learning assisted non-contact defect identification method using diffraction phase microscopy

Reliable detection of defects from optical fringe patterns is a crucial problem in non-destructive optical interfero-metric metrology. In this work, we propose a deep-learning-based method for fringe pattern defect identification. By attributing the defect information to the fringe pattern's phase gradient, we compute the spatial phase deriv-atives using the deep learning model and apply the gradient map to localize the defect. The robustness of the proposed method is illustrated on multiple numerically synthesized fringe pattern defects at various noise levels. Further, the practical utility of the proposed method is substantiated for experimental defect identification in diffraction phase microscopy.& COPY; 2023 Optica Publishing Group

Automated summary

In this paper, a deep-learning-based method for identifying defects in optical fringe patterns is proposed. By attributing the defect information to the phase gradient of the fringe pattern, the spatial phase derivatives are computed using a deep learning model, and the gradient map is applied to localize the defect. The robustness of the proposed method is demonstrated on numerically synthesized fringe pattern defects with various noise levels. Furthermore, the practical utility of the proposed method is substantiated in experimental defect identification in diffraction phase microscopy.