arXiv subjects

Krzysztof Patorski

Publications and source records attributed to Krzysztof Patorski.

4 recordsLinked to original sources

arXiv2026

DeepBessel: deep learning-based full-field vibration profilometry using single-shot time-averaged interference microscopy

Full-field vibration profilometry is essential for dynamic characterizing microelectromechanical systems (MEMS/MOEMS). Time-averaged interferometry (TAI) encodes spatial information about MEMS or MOEMS vibration amplitude in the interferogram's amplitude modulation using Bessel function (besselogram). Classical approaches for interferogram analysis are specialized for cosine function fringe patterns and therefore introduce reconstruction errors for besselogram decoding. This paper presents the DeepBessel: a deep learning-based approach for single-shot TAI interferogram analysis. A convolutional neural network (CNN) was trained using synthetic data, where the input consisted of besselograms, and the output corresponded to the underlying vibration amplitude distribution. Numerical validation and experimental testing demonstrated that DeepBessel significantly reduces reconstruction errors compared to the state-of-the-art approaches, e.g., Hilbert Spiral Transform (HST) method. The proposed network effectively mitigates errors caused by the mismatch between the Bessel and cosine functions. The results indicate that deep learning can improve the accuracy of full-field vibration measurements, offering new possibilities for optical metrology in MEMS or MOEMS applications.

physics.optics↗

arXiv2023

DeepOrientation: convolutional neural network for fringe pattern orientation map estimation

Fringe pattern based measurement techniques are the state-of-the-art in full-field optical metrology. They 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 orientation map can significantly facilitate the measurement process on various ways, e.g., fringe filtering (denoising), fringe pattern boundary padding, fringe skeletoning (contouring/following/tracking), local fringe spatial frequency (fringe period) estimation and fringe pattern phase demodulation. Considering all of that the accurate, robust and preferably automatic estimation of local fringe orientation map is of high importance. In this paper we propose novel numerical solution for local fringe orientation map estimation based on convolutional neural network and deep learning called DeepOrientation. Numerical simulations and experimental results corroborate the effectiveness of the proposed DeepOrientation comparing it with the representative of the classical approach to orientation estimation called combined plane fitting/gradient method. The example proving the effectiveness of DeepOrientation in fringe pattern analysis, which we present in this paper is the application of DeepOrientation for guiding the phase demodulation process in Hilbert spiral transform. In particular, living HeLa cells quantitative phase imaging outcomes verify the method as an important asset in label-free microscopy.

eess.IV↗

arXiv2022

Hilbert phase microscopy based on pseudo thermal illumination in Linnik configuration

Quantitative phase microscopy (QPM) is often based on recording an object-reference interference pattern and its further phase demodulation. We propose Pseudo Hilbert Phase Microscopy (PHPM) where we combine pseudo thermal light source illumination and Hilbert spiral transform phase demodulation to achieve hybrid hardware-software-driven noise robustness and increase in resolution of single-shot coherent QPM. Those advantageous features stem from physically altering the laser spatial coherence and numerically restoring spectrally overlapped object spatial frequencies. Capabilities of the PHPM are demonstrated analyzing calibrated phase targets and live HeLa cells in comparison with laser illumination and phase demodulation via temporal phase shifting and Fourier transform techniques. Performed studies verified unique ability of the PHPM to couple single-shot imaging, noise minimization, and preservation of phase details.

physics.optics↗

arXiv2022

Tailoring 2D Fast Iterative Filtering algorithm for low-contrast optical fringe pattern preprocessing

Retrieving object phase from the optical fringe pattern is a critical task in quantitative phase imaging and often requires appropriate image preprocessing (background and noise minimization), especially when retrieving phase from the single-shot fringe pattern image. In this article, for the first time, we propose to adapt the 2D Fast Iterative Filtering (FIF) method for fringe pattern decomposition and develop a novel version of FIF called the 2D fringe pattern Fast Iterative Filtering (fpFIF2), that is tailored for fringe pattern preprocessing. We show the positive influence of fpFIF2 onto fringe pattern filtering comparing to the previous 2D FIF implementation regarding processing speed, quality, and usage comfortability. We also compare the fpFIF2 with other state-of-the-art fringe pattern filtering methods in terms of aiding the Hilbert spiral transform method in phase retrieval. Employing numerical simulations and experimental fringe analysis, we prove that fpFIF2 outperforms reference methods, especially in terms of low-fringe-contrast phase reconstruction quality and decomposition time.

physics.optics↗