arXiv subjects

Jaromír Běhal

Publications and source records attributed to Jaromír Běhal.

3 recordsLinked to original sources

arXiv2026

From Stars to Molecules: AI Guided Device-Agnostic Super-Resolution Imaging

Super-resolution imaging has revolutionized the study of systems ranging from molecular structures to distant galaxies. However, existing super-resolution methods require extensive calibration and retraining for each imaging setup, limiting their practical deployment. We introduce a device-agnostic deep-learning framework for super-resolution imaging of point-like emitters that eliminates the need for calibration data or explicit knowledge of optical system parameters. Our device-agnostic modeling utilizes diverse, numerically simulated dataset encompassing a broad range of imaging conditions, enabling generalization across different optical setups. Once trained, the model reconstructs super-resolved images directly from a single resolution-limited camera frame with superior accuracy and computational efficiency compared to state-of-the-art methods. We experimentally validate our approach using a custom microscopy setup with controllable ground-truth emitter positions. We also demonstrate its versatility on stellar astronomy and single-molecule localization microscopy datasets of point-like sources, achieving high resolution without prior information. Our findings establish a pathway toward universal, calibration-free super-resolution imaging, expanding its applicability across scientific disciplines.

physics.optics↗

arXiv2026

Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy

Reliable identification of microplastic fibers is crucial for environmental monitoring but remains analytically challenging. We report an explainable deep-learning framework for classifying microplastic and natural microfibers using polarization-resolved digital holographic microscopy. From multiplexed holograms, the complex Jones matrix of each fiber was reconstructed to extract polarization eigen-parameters describing optical anisotropy. Statistical descriptors of nine polarization characteristics formed a 72-dimensional feature vector for a total of 296 fibers spanning six material classes, including polyamide 6, polyethylene terephthalate, polyamide 6.6, polypropylene, cotton and wool. The designed fully connected deep neural network achieved an accuracy of 96.7 % on the validation data, surpassing that of common machine-learning classifiers. Explainable artificial intelligence analysis with Shapley additive explanations identified eigenvalue-ratio quantities as dominant predictors, revealing the physical basis for classification. An additional reduced-feature model with the preserved architecture exploiting only these most significant eigenvalue-based characteristics retained high accuracy (93.3 %), thereby confirming their dominant role while still outperforming common machine-learning classifiers. These results establish polarization-based features as distinctive optical fingerprints and demonstrate the first explainable deep-learning approach for automated microplastic fiber identification.

physics.optics↗

arXiv2025

Incoherent lateral shearing digital holographic microscopy

The ability to resolve and quantify features at submicrometer scales from a single-shot image is crucial for real-time uncovering intricate structures in unlabeled biological samples and analyzing them at the subcellular level. We introduce a novel incoherent quantitative phase imaging technique based on lateral shearing digital holographic microscopy, with shearing distances exceeding the coherence area of the employed illumination -- a regime not previously achieved and exploited. This strategy consequently assures artifacts-free, high-accuracy, and high-resolution quantitative phase reconstructions. This regime extends the single-shot lateral shearing digital holographic microscopy towards incoherent illumination, thus increasing the space-time bandwidth product of the method. The practical common-path geometry also provides enhanced vibration resistance, which is essential for consistent time-lapse measurements. We verify the scalability and effectiveness of the method by investigating samples via multiple condenser-objective pairs, providing a wide range of lateral resolutions and fields of view, thereby assuring its applicability for various microscope settings. We experimentally verify long-term phase stability and unprecedented phase-reconstruction accuracy. Finally, we use our method for investigation of biological samples, including cheek cells, diatoms, and yeast cells, highlighting its potential for dynamic label-free analysis at the organelle level.

physics.optics↗