An unbiased risk estimator for image denoising in the presence of mixed poisson-gaussian noise

Self-supervised MRI denoising: leveraging Stein's unbiased risk estimator and spatially resolved noise maps

Thermal noise caused by the imaged object is an intrinsic limitation in magnetic resonance imaging (MRI), resulting in an impaired clinical value of the acquisitions. Recently, deep learning (DL)-based denoising methods achieved promising results by extracting complex feature representations from large data sets. Most approaches are trained in a supervised manner by directly mapping noisy to noise-free ground-truth data and, therefore, require extensive paired data sets, which can be expensive or infeasible to obtain for medical imaging applications. In this work, a DL-based denoising approach is investigated which operates on complex-valued reconstructed magnetic resonance (MR) images without noise-free target data. An extension of Stein's unbiased risk estimator (SURE) and spatially resolved noise maps quantifying the noise level with pixel accuracy were employed during the training process. Competitive denoising performance was achieved compared to supervised training with mean squared error (MSE) despite optimizing the model without noise-free target images. The proposed DL-based method can be applied for MR image enhancement without requiring noise-free target data for training. Integrating the noise maps as an additional input channel further enables the regulation of the desired level of denoising to adjust to the preference of the radiologist.

Edge effect of wide spectrum denoising in super-resolution microscopy

During the stochastic optical reconstruction microscope (STORM) raw image acquisition in super-resolution microscopy, noise is inevitable. Noise not only reduces the temporal and spatial resolution of the super-resolution image but also leads to the failure of super-resolution image reconstruction. Wide spectrum denoising (WSD) can effectively remove various random noises (such as Poisson noise and Gaussian noise) from the STORM raw image to improve the super-resolution image reconstruction. We found that there is an obvious edge effect in WSD, and its influence on STORM raw image denoising and super-resolution image reconstruction is studied. We then proposed the method of restraining edge effect. The simulation and real experiment results show that edge trimming can effectively suppress the edge effect, thus leading to better super-resolution image reconstruction.

Research on Long Jump Posture in School Physical Education Teaching Based on Video Analysis

Based on video, the human movement can be analyzed to achieve scientific training and skill improvement. Specifically, according to the video data during the movement, the human body can be detected and tracked, and relevant trajectory data can be obtained. On this basis, key motion parameters can be obtained and quantitative analysis of motion can be achieved. This paper uses video processing technologies to analyze the long jump posture in physical education. According to the video sequences measured during the athlete's long jump, the target detection and tracking algorithms are used to obtain the athlete's trajectory after preprocessing. Afterwards, further processing is carried out to calculate speed, angle, posture, and other related information to assist scientific sports training. The experimental results based on the measured data show that the algorithm can realize the analysis of the long jump scene and complete the quantitative analysis of the key indicators of the athletes. The research results can effectively support school physical education and guidance training and also provide a reference for other competitive video analysis.

Self-Supervised Poisson-Gaussian Denoising

We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised models for denoising learn to denoise from only noisy data and do not require corresponding clean images, which are difficult or impossible to acquire in some application areas of interest such as low-light microscopy. We introduce a new training strategy to handle Poisson-Gaussian noise which is the standard noise model for microscope images. Our new strategy eliminates hyperparameters from the loss function, which is important in a self-supervised regime where no ground truth data is available to guide hyperparameter tuning. We show how our denoiser can be adapted to the test data to improve performance. Our evaluations on microscope image denoising benchmarks validate our approach.

Trends in Super-High-Definition Imaging Techniques Based on Deep Neural Networks

Images captured by cameras in closed-circuit televisions and black boxes in cities have low or poor quality owing to lens distortion and optical blur. Moreover, actual images acquired through imaging sensors of cameras such as charge-coupled devices and complementary metal-oxide-semiconductors generally include noise with spatial-variant characteristics that follow Poisson distributions. If compression is directly applied to an image with such spatial-variant sensor noises at the transmitting end, complex and difficult noises called compressed Poisson noises occur at the receiving end. The super-high-definition imaging technology based on deep neural networks improves the image resolution as well as effectively removes the undesired compressed Poisson noises that may occur during real image acquisition and compression as well as in transmission and reception systems. This solution of using deep neural networks at the receiving end to solve the image degradation problem can be used in the intelligent image analysis platform that performs accurate image processing and analysis using high-definition images obtained from various camera sources such as closed-circuit televisions and black boxes. In this review article, we investigate the current state-of-the-art super-high-definition imaging techniques in terms of image denoising for removing the compressed Poisson noises as well as super-resolution based on the deep neural networks.

Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning

Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network's generalization strength to unseen additive noise levels. We also adapt the fusion denoising network architecture for image denoising on real images. Our approach improves real-world grayscale additive image denoising PSNR results for training noise levels and further on noise levels not seen during training. It also improves state-of-the-art color image denoising performance on every single noise level, by an average of 0.1dB, whether trained on or not.

Robust contrast-transfer-function phase retrieval via flexible deep learning networks

By exploiting the total variation (TV) regularization scheme and the contrast transfer function (CTF), a phase map can be retrieved from single-distance coherent diffraction images via the sparsity of the investigated object. However, the CTF-TV phase retrieval algorithm often struggles in the presence of strong noise, since it is based on the traditional compressive sensing optimization problem. Here, convolutional neural networks, a powerful tool from machine learning, are used to regularize the CTF-based phase retrieval problems and improve the recovery performance. This proposed method, the CTF-Deep phase retrieval algorithm, was tested both via simulations and experiments. The results show that it is robust to noise and fast enough for high-resolution applications, such as in optical, x-ray, or terahertz imaging.

An Improved Denoising Method for Partial Discharge Signals Contaminated by White Noise Based on Adaptive Short-Time Singular Value Decomposition

To extract partial discharge (PD) signals from white noise efficiently, this paper proposes a denoising method for PD signals, named adaptive short-time singular value decomposition (ASTSVD). First, a sliding window was moved along the time axis of a PD signal to cut a whole signal into segments with overlaps. The singular value decomposition (SVD) method was then applied to each segment to obtain its singular value sequence. The minimum description length (MDL) criterion was used to determine the number of effective singular values automatically. Then, the selected singular values of each signal segment were used to reconstruct the noise-free signal segment, from which the denoised PD signal was obtained. To evaluate ASTSVD, we applied ASTSVD and two other methods on simulated, laboratory-measured, and field-detected noisy PD signals, respectively. Compared to the other two methods, the denoised PD signals of ASTSVD contain less residual noise and exhibit smaller waveform distortion.

A Feature based Reconstruction Model for Fluorescence Microscopy Image Denoising

The advent of Fluorescence Microscopy over the last few years have dramatically improved the problem of visualization and tracking of specific cellular objects for biological inference. But like any other imaging system, fluorescence microscopy has its own limitations. The resultant images suffer from the effect of noise due to both signal dependent and signal independent factors, thereby limiting the possibility of biological inferencing. Denoising is a class of image processing algorithms that aim to remove noise from acquired images and has gained wide attention in the field of fluorescence microscopy image restoration. In this paper, we propose an image denoising algorithm based on the concept of feature extraction through multifractal decomposition and then estimate a noise free image from the gradients restricted to these features. Experimental results over simulated and real fluorescence microscopy data prove the merit of the proposed approach, both visually and quantitatively.

Compressed Blind Deconvolution and Denoising for Complementary Beam Subtraction Light-Sheet Fluorescence Microscopy

OBJECTIVE

The side-lobes of a Bessel beam (BB) create a severe out-of-focus background in scanning light-sheet fluorescence microscopy, thereby extremely limiting the axial resolution. The complementary beam subtraction (CBS) method can significantly reduce the out-of-focus background by double scanning a BB and its complementary beam. However, the blurring and noise caused by the system instability during the double scanning and subtraction operations degrade the image quality significantly. Therefore, we propose a compressed blind deconvolution and denoising (CBDD) method that solves this problem.

METHODS

We use a unified formulation that comprehensively takes advantage of multiple compressed sensing reconstructions and blind sparse representation.

RESULTS

The simulations and experiments were performed using the microbeads and model organisms to verify the effectiveness of the proposed method. Compared with the CBS light-sheet method, the proposed CBDD algorithm achieved the gain improvement in the axial and lateral resolution of about 1.81 and 2.22 times, respectively, while the average signal-to-noise ratio (SNR) was increased by about 3 dB.

CONCLUSION

Accordingly, the proposed method can suppress the noise level, enhance the SNR, and recover the degraded resolution simultaneously.

SIGNIFICANCE

The obtained results demonstrate the proposed CBDD algorithm is well suited to improve the imaging performance of the CBS light-sheet fluorescence microscopy.

External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising

Most of existing image denoising methods learn image priors from either external data or the noisy image itself to remove noise. However, priors learned from external data may not be adaptive to the image to be denoised, while priors learned from the given noisy image may not be accurate due to the interference of corrupted noise. Meanwhile, the noise in real-world noisy images is very complex, which is hard to be described by simple distributions such as Gaussian distribution, making real-world noisy image denoising a very challenging problem. We propose to exploit the information in both external data and the given noisy image, and develop an external prior guided internal prior learning method for real-world noisy image denoising. We first learn external priors from an independent set of clean natural images. With the aid of learned external priors, we then learn internal priors from the given noisy image to refine the prior model. The external and internal priors are formulated as a set of orthogonal dictionaries to efficiently reconstruct the desired image. Extensive experiments are performed on several real-world noisy image datasets. The proposed method demonstrates highly competitive denoising performance, outperforming state-of-the-art denoising methods including those designed for real-world noisy images.

PURE-LET Image Deconvolution

We propose a non-iterative image deconvolution algorithm for data corrupted by Poisson or mixed Poisson-Gaussian noise. Many applications involve such a problem, ranging from astronomical to biological imaging. We parameterize the deconvolution process as a linear combination of elementary functions, termed as linear expansion of thresholds. This parameterization is then optimized by minimizing a robust estimate of the true mean squared error, the Poisson unbiased risk estimate. Each elementary function consists of a Wiener filtering followed by a pointwise thresholding of undecimated Haar wavelet coefficients. In contrast to existing approaches, the proposed algorithm merely amounts to solving a linear system of equations, which has a fast and exact solution. Simulation experiments over different types of convolution kernels and various noise levels indicate that the proposed method outperforms the state-of-the-art techniques, in terms of both restoration quality and computational complexity. Finally, we present some results on real confocal fluorescence microscopy images and demonstrate the potential applicability of the proposed method for improving the quality of these images.We propose a non-iterative image deconvolution algorithm for data corrupted by Poisson or mixed Poisson-Gaussian noise. Many applications involve such a problem, ranging from astronomical to biological imaging. We parameterize the deconvolution process as a linear combination of elementary functions, termed as linear expansion of thresholds. This parameterization is then optimized by minimizing a robust estimate of the true mean squared error, the Poisson unbiased risk estimate. Each elementary function consists of a Wiener filtering followed by a pointwise thresholding of undecimated Haar wavelet coefficients. In contrast to existing approaches, the proposed algorithm merely amounts to solving a linear system of equations, which has a fast and exact solution. Simulation experiments over different types of convolution kernels and various noise levels indicate that the proposed method outperforms the state-of-the-art techniques, in terms of both restoration quality and computational complexity. Finally, we present some results on real confocal fluorescence microscopy images and demonstrate the potential applicability of the proposed method for improving the quality of these images.

Denoising time-resolved microscopy image sequences with singular value thresholding

Time-resolved imaging in microscopy is important for the direct observation of a range of dynamic processes in both the physical and life sciences. However, the image sequences are often corrupted by noise, either as a result of high frame rates or a need to limit the radiation dose received by the sample. Here we exploit both spatial and temporal correlations using low-rank matrix recovery methods to denoise microscopy image sequences. We also make use of an unbiased risk estimator to address the issue of how much thresholding to apply in a robust and automated manner. The performance of the technique is demonstrated using simulated image sequences, as well as experimental scanning transmission electron microscopy data, where surface adatom motion and nanoparticle structural dynamics are recovered at rates of up to 32 frames per second.

Fluorescence microscopy image noise reduction using a stochastically-connected random field model

Fluorescence microscopy is an essential part of a biologist’s toolkit, allowing assaying of many parameters like subcellular localization of proteins, changes in cytoskeletal dynamics, protein-protein interactions, and the concentration of specific cellular ions. A fundamental challenge with using fluorescence microscopy is the presence of noise. This study introduces a novel approach to reducing noise in fluorescence microscopy images. The noise reduction problem is posed as a Maximum A Posteriori estimation problem, and solved using a novel random field model called stochastically-connected random field (SRF), which combines random graph and field theory. Experimental results using synthetic and real fluorescence microscopy data show the proposed approach achieving strong noise reduction performance when compared to several other noise reduction algorithms, using quantitative metrics. The proposed SRF approach was able to achieve strong performance in terms of signal-to-noise ratio in the synthetic results, high signal to noise ratio and contrast to noise ratio in the real fluorescence microscopy data results, and was able to maintain cell structure and subtle details while reducing background and intra-cellular noise.

Color Image Denoising via Discriminatively Learned Iterative Shrinkage

In this paper, we propose a novel model, a discriminatively learned iterative shrinkage (DLIS) model, for color image denoising. The DLIS is a generalization of wavelet shrinkage by iteratively performing shrinkage over patch groups and whole image aggregation. We discriminatively learn the shrinkage functions and basis from the training pairs of noisy/noise-free images, which can adaptively handle different noise characteristics in luminance/chrominance channels, and the unknown structured noise in real-captured color images. Furthermore, to remove the splotchy real color noises, we design a Laplacian pyramid-based denoising framework to progressively recover the clean image from the coarsest scale to the finest scale by the DLIS model learned from the real color noises. Experiments show that our proposed approach can achieve the state-of-the-art denoising results on both synthetic denoising benchmark and real-captured color images.