White blood cells (WBC) play a significant role in human immune system, so WBC detection is a meaningful work. In this paper, we propose a novel framework which combines Fourier ptychographic microscopy (FPM) and SO-you only look once (YOLO) for WCB detection. FPM is a recently developed microscope technology which can achieve high-resolution, wide-field, and quantitative phase imaging at the same time without mechanical moving and phase measurement. With the FPM, we can get high resolution, wide field-of-view blood cell images at one time. After obtaining high-resolution images, we propose SO-YOLO as our detection method. As a convolutional neural network, the SO-YOLO outperforms the state-of-the-art detection methods both in accuracy and speed. The proposed framework in this paper can be used in clinical diagnose, because the experiment setup is flexible and the detection is fast. The data set in this paper is made with FPM by ourselves. Our data set contains 1000 color high resolution images and all the WBC has been detected and counted by a human expert. The detection results by the experts are regarded as the ground truth. The experiment results show that the SO-YOLO performs well in detecting small objects compared with other methods.

Limited resolution is one of the most important factors hindering the application of remote sensing images (RSIs). Single-image super resolution (SISR) is a technique to improve the spatial resolution of digital images and has attracted the attention of many researchers. In recent years, with the advancement of deep learning (DL) frameworks, many DL-based SISR models have been proposed and achieved state-of-the-art performance; however, most SISR models for RSIs use the bicubic downsampler to construct low-resolution (LR) and high-resolution (HR) training pairs. Considering that the quality of the actual RSIs depends on a variety of factors, such as illumination, atmosphere, imaging sensor responses, and signal processing, training on “ideal” datasets results in a dramatic drop in model performance on real RSIs. To address this issue, we propose to build a more realistic training dataset by modeling the degradation with blur kernels and imaging noises. We also design a novel residual balanced attention network (RBAN) as a generator to estimate super-resolution results from the LR inputs. To encourage RBAN to generate more realistic textures, we apply a UNet-shape discriminator for adversarial training. Both referenced evaluations on synthetic data and non-referenced evaluations on actual images were carried out. Experimental results validate the effectiveness of the proposed framework, and our model exhibits state-of-the-art performance in quantitative evaluation and visual quality. We believe that the proposed framework can facilitate super-resolution techniques from research to practical applications in RSIs processing.

Label noise and class imbalance are common challenges encountered in real-world datasets. Existing approaches for robust learning often focus on addressing either label noise or class imbalance individually, resulting in suboptimal performance when both biases are present. To bridge this gap, this work introduces a novel meta-learning-based dynamic loss that adapts the objective functions during the training process to effectively learn a classifier from long-tailed noisy data. Specifically, our dynamic loss consists of two components: a label corrector and a margin generator. The label corrector is responsible for correcting noisy labels, while the margin generator generates per-class classification margins by capturing the underlying data distribution and the learning state of the classifier. In addition, we employ a hierarchical sampling strategy that enriches a small amount of unbiased metadata with diverse and challenging samples. This enables the joint optimization of the two components in the dynamic loss through meta-learning, allowing the classifier to effectively adapt to clean and balanced test data. Extensive experiments conducted on multiple real-world and synthetic datasets with various types of data biases, including CIFAR-10/100, Animal-10N, ImageNet-LT, and Webvision, demonstrate that our method achieves state-of-the-art accuracy.

Fourier ptychographic microscopy (FPM) is a recently developed microscope technology that overcomes the resolution limit of a low numerical aperture (NA) objective lens by employing angular varying illuminations. Combining the concepts of ptychography, synthetic aperture and phase retrieval, FPM achieves high-resolution, wide-field and quantitative phase imaging at the same time. In typical FPM systems, the angular varying illuminations are achieved with LED arrays whose positional misalignments bring significant errors in the reconstruction procedure. In previous studies, several LED array alignment methods are developed, which iteratively recover the positional misalignment parameters during the reconstruction. These methods consume additional calculations in FPM reconstruction and may not be practical in other microscopy system. In this work, we represent a preprocessing LED array alignment method by accurately localizing the brightfield area on the sample plane. By applying Particle Swarm Optimization (PSO) method and Random Sample Consensus (RANSAC) method, the global misalignment parameters can be estimated with high accuracy and speed. Both numerical simulations and actual system experiments are carried out to evaluate the effectiveness of our method and the results show that the reconstruction quality of high-resolution images is significantly improved by using our method.

Fourier ptychographic microscopy (FPM) is a recently developed microscope that offers wide field, high resolution and quantitative phase imaging. Combining the concepts of ptychography, synthetic aperture and phase retrieval, FPM overcomes the space-bandwidth-product (SBP) limit of the optical system. In FPM, a LED array is used as the illumination module and specimen images illuminated with angular varying illuminations are captured. These images are synthesized to recover the high SBP complex field of the specimen. There has been many improvements of FPM since its appearance and FPM is of great potential in the field of hematology and pathology. However, low efficiency in capturing data, especially in the situation of capturing all three color channels, limits the application of FPM. Although spectral multiplex strategy for FPM is developed, the reconstruction quality and speed is decreased for exchanging the capture efficiency. In other hand, the reconstruction quality of FPM is significantly degraded by the imaging noise in the dark-field images because the high-frequency information in dark-field images is of low energy and contaminated by noise. In this paper, we propose an efficient colorful FPM reconstruction method using multi-resolution wavelet color fusion. We also propose an adaptive denoising method by analyzing the noise information of the dark-frame. Both simulation and experiment results are carried out to validate our methods. Results demonstrate that the imaging noise is suppressed and the colorful reconstruction is of high efficiency and quality.