Mingli Zhang

Image denoising based on sparse representation and gradient histogram

Various image priors, such as sparsity prior, non-local self-similarity prior and gradient histogram prior, have been widely used for noise removal, while preserving the image texture. However, the gradient histogram prior used for texture enhancement sometimes generates false textures in the smooth areas. In order to address these problems, the authors propose a robust algorithm combining gradient histogram with sparse representation to obtain good estimates of the sparse coding coefficients of the latent image and realising image denoising while preserving the texture. The proposed model is solved by having a balance between over-enhancement and over-smoothing of the texture in order to preserve the natural texture appearance. Experimental results demonstrate the efficiency and effectiveness of the proposed method.

Effective document image deblurring via gradient histogram preservation

Traditional deblurring algorithms are often focused on natural-scaled images, which are not adapted for document texts and images without having some negative impacts on the accuracy of the OCR and the visual quality. In this paper, we propose a gradient histogram preservation method. An effective optimization method was developed and achieves satisfying results for kernel estimation. By combining the gradient histogram preservation prior with conventional image deblurring methods, it significantly improves the simulations and experimental results on document images and a high SSIM is achieved with the proposed method.

Atlas-based reconstruction of high performance brain MR data

Abstract Image priors based on total variation (TV) and nonlocal patch similarity have shown to be powerful techniques for the reconstruction of magnetic resonance (MR) images from undersampled k-space measurements. However, due to the uniform regularization of gradients, standard TV approaches often over-smooth edges in the image, resulting in the loss of important details. This paper proposes a novel compressed sensing method which combines both external and internal information for the high-performance reconstruction of MRI data. A probabilistic atlas is used to model the spatial distribution of gradients that correspond to various anatomical structures in the image. This atlas is then employed to control the level of gradient regularization at each image location, within a weighted TV regularization prior. The proposed method also leverages the redundancy of nonlocal similar patches through a sparse representation model. Experiments on T1-weighted images from the ABIDE dataset show the proposed method to outperform state-of-the-art approaches, for different sampling rates and noise levels.

Medical image super-resolution with non-local embedding sparse representation and improved IBP

This paper proposes a novel super-resolution method that exploits the sparse representation and non-local similarity of patches for the effective reconstruction of images. High-resolution images are reconstructed from low resolution observations with an efficient technique based on the alternating direction method of multipliers (ADMM). A robust iterative back-projection approach is used in a post-processing step to remove residual noise and artifacts in the reconstructed image. Experiments on benchmark medical images illustrate the advantage of our method, in terms of PSNR and SSIM, compared to state of the art approaches.

Robust MRI reconstruction via re-weighted total variation and non-local sparse regression

Total variation (TV) based sparsity and non local self-similarity have been shown to be powerful tools for the reconstruction of magnetic resonance (MR) images. However, due to the uniform regularization of gradient sparsity, standard TV approaches often over-smooth edges in the image, resulting in the loss of important details. This paper presents a novel compressed sensing method for the reconstruction of MRI data, which uses a regularization strategy based on re-weighted TV to preserve image edges. This method also leverages the redundancy of non local image patches through the use of a sparse regression model. An efficient strategy based on the Alternating Direction Method of Multipliers (ADMM) algorithm is used to recover images with the proposed model. Experimental results on a simulated phantom and real brain MR data show our method to outperform state-of-the-art compressed sensing approaches, by better preserving edges and removing artifacts in the image.

A weighted total variation approach for the atlas-based reconstruction of brain MR data

Compressed sensing is a powerful approach to reconstruct high-quality images using a small number of samples. This paper presents a novel compressed sensing method that uses a probabilistic atlas to impose spatial constraints on the reconstruction of brain magnetic resonance imaging (MRI) data. A weighted total variation (TV) model is proposed to characterize the spatial distribution of gradients in the brain, and incorporate this information in the reconstruction process. Experiments on T1-weighted MR images from the ABIDE dataset show our proposed method to outperform the standard uniform TV model, as well as state-of-the-art approaches, for low sampling rates and high noise levels.

Structure preserving image denoising based on low-rank reconstruction and gradient histograms

Abstract One of the main challenges of denoising approaches is preserving images details, like textures and edges, while suppressing noise. The preservation of such details is essential to ensure good quality, especially in high-resolution images. This paper presents a novel denoising method that combines a low-rank regularization of similar non-local patches with a texture preserving prior based on the histogram of gradients. A dynamic thresholding operator, deriving from the weighted nuclear norm, is also used to reconstruct groups of similar patches more accurately, by applying less shrinkage to the larger singular values. Moreover, an efficient iterative approach based on the ADMM algorithm is proposed to compute the denoised image, under low-rank and histogram preservation constraints. Experiments on two benchmark datasets of high-resolution images show that the proposed method to outperform state-of-the-art approaches, for all noise levels.

Image completion with global structure and weighted nuclear norm regularization

Structure and nonlocal patch similarity have been used successfully to enhance the performance of image restoration. However, these techniques can often remove textures and edges, or introduce artifacts. In this paper, we propose a novel image completion method that leverages the redundancy of nonlocal image patches via the low-rank regularization of similar patch groups. The textures and edges in these patches are preserved using an adaptive regularization technique based on the weighted nuclear norm. Furthermore, a new global structure regularization strategy, imposing ℓ1-norm sparsity on the images high-frequency residual component, is presented to recover missing pixels while preserving structural information in the image. An efficient optimization technique, based on the Alternating Direction Method of Multipliers (ADMM) algorithm, is used to solve the proposed model. Experimental results show our method to outperform state-of-the-art image completion approaches, for various text-corrupted images and different ratios of missing pixels.

Effective compressive sensing via reweighted total variation and weighted nuclear norm regularization

Total variation (TV) and non-local patch similarity have been used successfully to enhance the performance of compressive sensing (CS) approaches. However, such techniques can often remove important details in the image or introduce reconstruction artifacts. This paper presents a novel CS method, which uses an adaptive reweighted TV strategy to better preserve image edges. Our method also leverages the redundancy of non-local image patches through the use of weighted low rank regularization. An optimization strategy based on the ADMM algorithm is used to reconstruct images efficiently. Experimental results show our method to outperform state-of-the-art CS approaches, for various sampling ratios.

LRI: A low rank approach to non-local sparse representation for image interpolation

The sparse representation models for image super-resolution have shown great potential in various imaging and vision tasks. However, most of them are challenged by the accuracy issue especially when images are significantly down-sampled. In this paper, we aim to improve the performance of sparse representation. We propose to incorporate a low rank approach into image non-local sparse representation model. To the best of our knowledge, this is the first work to integrate low rank approaches into non-local spare representation for image interpolation. The proposed method can obtain good estimation of sparse coefficients of original images. Experimental results show the effectiveness of our proposed method compared with the state-of-the-art.