Edge-aware image denoising algorithm

An ideal compression method for neutron radiation image should have high compression ratio while keeping more details of the original image. Compressed sensing (CS), which can break through the restrictions of sampling theorem, is likely to offer an efficient compression scheme for the neutron radiation image. Combining wavelet transform with directional filter banks, a novel nonredundant multiscale geometry analysis transform named Wavelet Directional Filter Banks (WDFB) is constructed and applied to represent neutron radiation image sparsely. Then, the block-based CS technique is introduced and a high performance CS scheme for neutron radiation image is proposed. By performing two-step iterative shrinkage algorithm the problem of L1 norm minimization is solved to reconstruct neutron radiation image from random measurements. The experiment results demonstrate that the scheme not only improves the quality of reconstructed image obviously but also retains more details of original image.

The widely used wavelet-thresholding techniques (DWT-H and DWT-S) have a near-optimal behavior that cannot be enhanced by any local denoising filter, but they cannot utilize the similarity of small-size image patches to enhance the denoising performance. Two of the latest improvements (WNLM and NLMW) introduced the Euclidean distance to measure the similarity of image patches, and then used the non-local meaning of similar patches for further denoising. Since the Euclidean distance is not a good similarity measurement, these two improvements are limited. In this study, we introduced the earth mover’s distance (EMD) as the similarity measure of small-scale patches within the wavelet sub-bands of noisy images. Moreover, at higher noise levels, we further incorporated joint bilateral filtering, which can filter both the spatial domain and the intensity domain of images. Denoising simulation experiments on BSDS500 demonstrated that our algorithm outperformed the DWT-H, DWT-S, WNLM, and NLMW algorithms by 4.197 dB, 3.326 dB, 2.097 dB, and 1.162 dB in terms of the average PSNR, and by 0.230, 0.213, 0.132, and 0.085 in terms of the average SSIM.

This paper proposes an image patch selection that finds similar patches in multiple images so that image denoising can suppress noise more effectively by exploiting the identified similar patches from the multi-view images. We encode all image patches in multi-view images into a low-dimensional space, and it allows for a denoiser to find similar patches effectively from the space. Our approach enables existing patch-based denoisers, which often find similar patches within an image window, to identify more similar patches by extending the limited search space into the entire space (i.e., all input images). We integrate our technique into state-of-the-art single-view denoising (block-matching and 3D filtering (BM3D)), and demonstrate that the BM3D combined with our approach is able to conduct multi-view image denoising effectively, without a major alteration to the existing algorithm.

Impulse noise reduction has been a challenge for Image Processing researchers for many decades. Median filter had been the most popular denoising methods. However, owing to its edge jittering and removing image detail properties, numerous efforts have been taken in order to improve its performance. Median ϵ-filter is one of the modified median filters. Median ϵ-filter and median filter behave in a like manner in the presence of noise. Thus, it has all disadvantageous things of median filter. In this article, we improve median ϵ-filter's efficiency by giving weights to the outcomes of ϵ-filter. The experimental results show the excellent performance of our method. Other than that, in the absence of noise, our method preserves the original image's details more than others.

It is important for image denoising methods with accurate noise level on real-world noisy images. Traditional noise level estimation methods either overestimate or underestimate the noise level. The former will make denoising methods smooth rich structures while the latter will make them reduce noise incompletely. To accurately estimate AGWN level, this paper proposes a novel blind additive Gaussian white noise level estimation method using Chi-square distribution, including the following key points: First, we select an initial flat patch set from the base image, which is decomposed from the noisy image by the relative total variation. And the initial noise level is estimated by mapping the patch set to the original noisy image. Then, we get the detail images by the usage of the directional gradient operations on the noisy image. Next, the initial flat patches are refined by a patch selection method with initial noise level and Chi-square distribution on the detail images. Finally, an iterative criterion is reemployed to generate a stable noise level. Experimental results validate that the proposed noise level estimation method is effective and is even superior to the state-of-the-arts.

This paper proposes a surface fitting algorithm for inspection of flat panel display(FPD) based on multilevel B-spline approximation(MBA). FPD devices have non-uniform background, and shape and intensity of defects are very various. MBA is useful algorithm for surface fitting but it is sensitive to number of control lattices. As level increases, details of original image can be reconstructed. To detect defect, defective area must not be well-reconstructed. In this paper, we propose a level decision method of MBA for FPD. After process of each level, we decide whether stop to increase level of MBA or not with simple distance measure. Experimental result shows that our proposed method makes to detect defects easy.

The solutions of equation-based noise detector for an adaptive median filter

Image-based individual recognition of giant pandas in real wild scenes suffers from difficulties such as occlusion and multiple postures. Image painting is an important preprocessing step in solving the occlusion of giant panda images. A two-stage inpainting model of giant panda images based on partial convolutions and multi-scale features is proposed. In the coarse inpainting, the structural in-formation of the occluded part is restored, while the fine inpainting focuses on re-storing details such as textures and edges based on the coarse inpainting. A new PatchGAN with two discriminators in the coarse inpainting balances two-scale information guided by the WGAN-GP loss and L1 norm. The generator of the new PatchGAN uses partial-convolutions to avoid the propagation and influence of misinformation in the occluded area. In the fine inpainting, a new proposed module fusing multi-scale feature by contextual attention is added to the PatchGAN. The fine inpainting model learns and enhances the texture and details of the image output by the coarse inpainting through the global searching for mul-ti-scale similar image patches by multi-scale context attention. Thus, it can strengthen the semantic connection between occluded and real image regions. In order to achieve better multi-scale inpainting results, the perceived loss and style loss are added to the adversarial loss. Compared with state-of-art methods, the proposed method can effectively restore image textures and details while sup-pressing noise and artifacts from visual effects. The PSNR, SSIM and FIN of proposed method can achieve 35.69, 0.971 and 5.22 respectively, indicating that proposed method can obtain satisfied inpainting results.

Current self-supervised denoising methods for paired noisy images typically involve mapping one noisy image through the network to the other noisy image. However, after measuring the spectral bias of such methods using our proposed Image Pair Frequency-Band Similarity, it suffers from two practical limitations. Firstly, the high-frequency structural details in images are not preserved well enough. Secondly, during the process of fitting high frequencies, the network learns high-frequency noise from the mapped noisy images. To address these challenges, we introduce a Spectral Controlling network (SCNet) to optimize self-supervised denoising of paired noisy images. First, we propose a selection strategy to choose frequency band components for noisy images, to accelerate the convergence speed of training. Next, we present a parameter optimization method that restricts the learning ability of convolutional kernels to high-frequency noise using the Lipschitz constant, without changing the network structure. Finally, we introduce the Spectral Separation and low-rank Reconstruction module (SSR module), which separates noise and high-frequency details through frequency domain separation and low-rank space reconstruction, to retain the high-frequency structural details of images. Experiments performed on synthetic and real-world datasets verify the effectiveness of SCNet. The code will be released soon.

In large scale vision applications, high-dimensional descriptors extracted from image patches are in large quantities. Thus hashing methods that compact descriptors to binary codes have been proposed to achieve practical resource consumption. Among these methods, unsupervised hashing aims to preserve Euclidean distances, which do not correlate well with the similarity of image patches. Supervised hashing methods exploit labeled data to learn binary codes based on visual or semantic similarity, which are usually slow to train and consider global structure of data. When data lie on a sub-manifold, global structure can not reflect the inherent structure well and may lead to incompact codes. We propose locality preserving hash (LPH) to learn affine robust binary codes. LPH preserves local structure by embedding data into a sub-manifold, and performing binarization that minimize false classification ratio while keeping partition balanced. Experiments on two datasets show that LPH is easy to train and performs better than state-of-the-art methods with more compact binary codes.KeywordsSimilarity SearchBinary Code LearningLocality Preserving HashLocality Preserving Projection

Machine learning-based image super-resolution (SR) has garnered increasing research interest in recent years. However, there are two issues that have not been adequately addressed. The first issue is that existing SR methods often overlook the importance of improving the quality of the training dataset, which is a crucial factor in determining SR performance, regardless of the training method employed. The second issue is that while some studies report high numerical metrics, the visual results remain unsatisfactory. To address the first problem, we propose a new image down-sampling method to obtain higher-quality training datasets. To tackle the second problem, we present a new image super-resolution model based on a large-size convolution kernel and a multi-path algorithm. Specifically, we use an adaptive large-size convolutional kernel to extract features from the image based on the size of the input image, and a residual network to generate a deeper model to retain more details of the original input image. Experimental results demonstrate that the proposed multilayer downsampling method (MDM) can significantly improve the visual quality compared to traditional downsampling methods. Moreover, our proposed method achieves the best peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values compared to several typical SR algorithms. Furthermore, subjective evaluation by human observers reveals that our method retains more details of the original image and produces smoother high-resolution images. Our proposed method effectively addresses the two aforementioned issues, which leads to improved SR performance in terms of both quantitative and qualitative measures.

Most of abdominal CT images include Gaussian noise, and CT scans form a blurry vision because of the internal fat tissue inside of abdomen. These two handicaps (noise and fat tissue) constitute an impediment in front of an accurate abdominal organ & tumour segmentation. Also segmentation techniques generally fall into error on segmentation of close grayscale regions. Therefore, denoising and enhancement parts are crucial for better segmentation results on CT images. In this paper, we form a tool including three efficient algorithms for the purpose of image enhancement before abdominal organ & tumour segmentation. At first, the denoising process is realized by Block Matching and 3D Filtering (BM3D) algorithm for elimination of Gaussian noise stated in arterial phase CT images. At second, Fast Linking Spiking Cortical Model (FL-SCM) is used for removing the internal fat tissue. At last, Otsu algorithm is processed to remove the redundant parts within the image. In experiments, Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) index are used to evaluate the performance of proposed method, and a visual comparison is presented. According to results, it is seen that proposed tool obtains the best PSNR and SSIM values in comparison with two steps of pipeline (FL-SCM and BM3D & FL-SCM). Consequently, BM3D & FL-SCM & Otsu (BFO) ensures a clean abdomen particularly for segmentation of liver, spleen, pancreas, adrenal tumours, aorta, ribs, spinal cord and kidneys.

Non-local similarity images play a huge role in image denoising tasks. Many of the existing denoising algorithms have problems in that the edge information is too smooth, the reconstruction details are insufficient, and artifacts are easily generated while removing noise. In order to solve these shortcomings and improve the denoising accuracy, we propose a denoising algorithm based on non-local similarity and adaptive singular value threshold (ASVT). The algorithm consists of three basic steps: block matching grouping, ASVT denoising, and aggregation. First, similar image patches are grouped by block matching method, and each similar block group is used as a group matrix for each column of the matrix. Then, under the framework of image non-local similarity and low rank approximation, the denoising problem is transformed into low rank matrix approximation problem, which is solved by ASVT. Finally, all processed image patches are aggregated to produce an initial denoised image. In order to effectively avoid the influence of noise residual on denoising, the denoising result is further improved by the back projection strategy, and more detailed features are retained. Experimental results clearly show that the proposed algorithm is competitive with the current state-of-the-art denoising algorithms in terms of both quantitative measure and subjective visual quality and can retain more details and improve the smoothing problem.

Blind image deconvolution, i.e., estimating both the latent image and the blur kernel from the only observed blurry image, is a severely ill-posed inverse problem. In this paper, we propose a blur kernel estimation method for blind motion deblurring using sparse representation and cross-scale self-similarity of image patches as priors to recover the latent sharp image from a single blurry image. Sparse representation indicates that image patches can always be represented well as a sparse linear combination of atoms in an appropriate dictionary. Cross-scale self-similarity results in that any image patch can in some way be well approximated by a number of other similar patches across different image scales. Our method is based on the observations that almost any image patch in a natural image has multiple similar patches in down-sampled versions of the image, and down-sampling produces image patches that are sharper than those in the blurry image itself. In our method, the dictionary for sparse representation is trained adaptively from sharper patches sampled from the down-sampled latent image estimate to make the similar patches of the latent sharp image well represented sparsely, and meanwhile, all patches from the latent image estimate are optimized to be as close to the sharper similar patches searched from the down-sampled version to enforce the sharp recovery of the latent image by constructing a non-local regularization. Experimental results on both simulated and real blurry images demonstrate that our method outperforms state-of-the-art blind deblurring methods.

The paper presents a new Convolutional Neural Network (CNN) architecture, called stacked stereo CNN, for computing disparity map from stereo images. In stacked stereo CNN, left and right image patches are stacked back-to-back and fed to a single tower CNN. This is in contrast to Siamese network where two towers are used, one for the left patch and other for the right patch. The proposed network is trained on a large set of similar and dissimilar image patches, which are generated from stereo images and their ground truth images from Middlebury stereo datasets. The network returns a dissimilarity score for a pair of image patch which is used to compute the cost volume. The cost volume is further refined using post processing steps before generating the final disparity map. The proposed network is evaluated on Middlebury datasets and achieves comparable results to the state-of-art algorithms.