Atmospheric Light Estimation Using Polarization Degree Gradient for Image Dehazing.

A number of image dehazing techniques depend on the estimation of atmospheric light intensity. The majority of dehazing algorithms do not incorporate a physical model to estimate atmospheric light, leading to reduced accuracy and significantly impacting the effectiveness of dehazing. This article presents a novel approach for estimating atmospheric light using the polarization state and polarization degree gradient of the sky. We utilize this approach to enhance the outcomes of image dehazing by applying it to pre-existing dehazing algorithms. Our study and development of a real-time dehazing system has shown that the approach we propose has a clear advantage over previous methods for estimating ambient light. After incorporating the proposed approach into existing defogging methods, a significant improvement in the effectiveness of defogging was noted through the assessment of various criteria such as contrast, PSNR, and SSIM.

High-resolution 3D Fourier ptychographic reconstruction using a hemispherical illumination source with multiplexed-coded strategy.

Fourier ptychography is a promising and flexible imaging technique that can achieve 2D quantitative reconstruction with higher resolution beyond the limitation of the system. Meanwhile, by using different imaging models, the same platform can be applied to achieve 3D refractive index reconstruction. To improve the illumination NA as much as possible while reducing the intensity attenuation problem caused by the LED board used in the traditional FP platform, we apply a hemispherical lighting structure and design a new LED arrangement according to 3D Fourier diffraction theory. Therefore, we could obtain the illumination of 0.98NA using 187 LEDs and achieve imaging half-pitch resolutions of ∼174 nm and ∼524 nm for the lateral and axial directions respectively, using a 40×/0.6NA objective lens. Furthermore, to reduce the number of captured images required and realize real-time data collection, we apply the multiplexed-coded illumination strategy and compare several coded patterns through simulation and experiment. Through comparison, we determined a radial-coded illumination pattern that could achieve more similar results as sequential scanning and increase the acquisition speed to above 1 Hz. Therefore, this paper provides the possibility of this technique in real-time 3D observation of in vitro live samples.

Double-flow convolutional neural network for rapid large field of view Fourier ptychographic reconstruction.

Fourier ptychographic microscopy is a promising imaging technique which can circumvent the space-bandwidth product of the system and achieve a reconstruction result with wide field-of-view (FOV), high-resolution and quantitative phase information. However, traditional iterative-based methods typically require multiple times to get convergence, and due to the wave vector deviation in different areas, the millimeter-level full-FOV cannot be well reconstructed once and typically required to be separated into several portions with sufficient overlaps and reconstructed separately, which makes traditional methods suffer from long reconstruction time for a large-FOV (of the order of minutes) and limits the application in real-time large-FOV monitoring of live sample in vitro. Here we propose a novel deep-learning based method called DFNN which can be used in place of traditional iterative-based methods to increase the quality of single large-FOV reconstruction and reducing the processing time from 167.5 to 0.1125 second. In addition, we demonstrate that by training based on the simulation dataset with high-entropy property (Opt. Express 28, 24 152 [2020]), DFNN could has fine generalizability and little dependence on the morphological features of samples. The superior robustness of DFNN against noise is also demonstrated in both simulation and experiment. Furthermore, our model shows more robustness against the wave vector deviation. Therefore, we could achieve better results at the edge areas of a single large-FOV reconstruction. Our method demonstrates a promising way to perform real-time single large-FOV reconstructions and provides further possibilities for real-time large-FOV monitoring of live samples with sub-cellular resolution.

Single full-FOV reconstruction Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) is a recently developed computational imaging technique that has high-resolution and wide field-of-view (FOV). FPM bypasses the NA limit of the system by stitching a number of variable-illuminated measured images in Fourier space. On the basis of the wide FOV of the low NA objective, the high-resolution image with a wide FOV can be reconstructed through the phase recovery algorithm. However, the high-resolution reconstruction images are affected by the LED array point light source. The results are: (1) the intensities collected by the sample are severely declined when edge LEDs illuminate the sample; (2) the multiple reconstructions are caused by wavevectors inconsistency for the full FOV images. Here, we propose a new lighting scheme termed full FOV Fourier ptychographic microscopy (F3PM). By combining the LED array and telecentric lens, the method can provide plane waves with different angles while maintaining uniform intensity. Benefiting from the telecentric performance and f‒θ property of the telecentric lens, the system stability is improved and the relationship between the position of LED and its illumination angle is simplified. The excellent plane wave provided by the telecentric lens guarantees the same wavevector in the full FOV, and we use this wavevector to reconstruct the full FOV during one time. The area and diameter of the single reconstruction FOV reached 14.6mm 2 and 5.4 mm, respectively, and the diameter is very close to the field number (5.5 mm) of the 4× objective. Compared with the traditional FPM, we have increased the diameter of FOV in a single reconstruction by ∼ 10 times, eliminating the complicated steps of computational redundancy and image stitching.

Neural network model combined with pupil recovery for Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) is a recently developed imaging approach aiming at circumventing the limitation of the space-bandwidth product (SBP) and acquiring a complex image with both wide field and high resolution. So far, in many algorithms that have been proposed to solve the FPM reconstruction problem, the pupil function is set to be a fixed value such as the coherent transfer function (CTF) of the system. However, the pupil aberration of the optical components in an FPM imaging system can significantly degrade the quality of the reconstruction results. In this paper, we build a trainable network (FINN-P) which combines the pupil recovery with the forward imaging process of FPM based on TensorFlow. Both the spectrum of the sample and pupil function are treated as the two-dimensional (2D) learnable weights of layers. Therefore, the complex object information and pupil function can be obtained simultaneously by minimizing the loss function in the training process. Simulated datasets are used to verify the effectiveness of pupil recovery, and experiments on the open source measured dataset demonstrate that our method can achieve better reconstruction results even in the presence of a large aberration. In addition, the recovered pupil function can be used as a good estimate before further analysis of the system optical transmission capability.

Apodized coherent transfer function constraint for partially coherent Fourier ptychographic microscopy.

Fourier ptychographic microscopy (FPM) is a recently developed computational microscopy approach that produces both wide field-of-view (FOV) and high resolution (HR) intensity and a phase image of the sample. Inspired by the ideas of synthetic aperture and phase retrieval, FPM iteratively stitches multiple low-resolution (LR) images with variable illumination angles in Fourier space to reconstruct an HR complex image. Typically, FPM illuminating the sample with an LED array is approximated as a coherent imaging process, and the coherent transfer function (CTF) is imposed as a support constraint in Fourier space. However, a millimeter-scale LED is inapposite to be treated as a coherent light source. As a result, the quality of reconstructed image is degraded by the inappropriate approximation. In this paper, we analyze the coherence of an FPM system and propose a novel constraint approach termed Apodized CTF (AC) constraint in Fourier space. Results on both simulated data and actual captured data show that this new constraint is more stable and robust than CTF. This approach can also relax the coherence requirement of illumination. In addition, it is simple, does not require additional computations, and is easy to be embedded in almost all the reconstruction algorithms proposed so far.