Yongqin Zhang

Image Super-Resolution Based on Structure-Modulated Sparse Representation

Sparse representation has recently attracted enormous interests in the field of image restoration. The conventional sparsity-based methods enforce sparse coding on small image patches with certain constraints. However, they neglected the characteristics of image structures both within the same scale and across the different scales for the image sparse representation. This drawback limits the modeling capability of sparsity-based super-resolution methods, especially for the recovery of the observed low-resolution images. In this paper, we propose a joint super-resolution framework of structure-modulated sparse representations to improve the performance of sparsity-based image super-resolution. The proposed algorithm formulates the constrained optimization problem for high-resolution image recovery. The multistep magnification scheme with the ridge regression is first used to exploit the multiscale redundancy for the initial estimation of the high-resolution image. Then, the gradient histogram preservation is incorporated as a regularization term in sparse modeling of the image super-resolution problem. Finally, the numerical solution is provided to solve the super-resolution problem of model parameter estimation and sparse representation. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed algorithm. Experimental results demonstrate that our proposed algorithm, which can recover more fine structures and details from an input low-resolution image, outperforms the state-of-the-art methods both subjectively and objectively in most cases.

Visibility enhancement using an image filtering approach

The misty, foggy, or hazy weather conditions lead to image color distortion and reduce the resolution and the contrast of the observed object in outdoor scene acquisition. In order to detect and remove haze, this article proposes a novel effective algorithm for visibility enhancement from a single gray or color image. Since it can be considered that the haze mainly concentrates in one component of the multilayer image, the haze-free image is reconstructed through haze layer estimation based on the image filtering approach using both low-rank technique and the overlap averaging scheme. By using parallel analysis with Monte Carlo simulation from the coarse atmospheric veil by the median filter, the refined smooth haze layer is acquired with both less texture and retaining depth changes. With the dark channel prior, the normalized transmission coefficient is calculated to restore fogless image. Experimental results show that the proposed algorithm is a simpler and efficient method for clarity improvement and contrast enhancement from a single foggy image. Moreover, it can be comparable with the state-of-the-art methods, and even has better results than them.

Joint image denoising using adaptive principal component analysis and self-similarity

The non-local means (NLM) has attracted enormous interest in image denoising problem in recent years. In this paper, we propose an efficient joint denoising algorithm based on adaptive principal component analysis (PCA) and self-similarity that improves the predictability of pixel intensities in reconstructed images. The proposed algorithm consists of two successive steps without iteration: the low-rank approximation based on parallel analysis, and the collaborative filtering. First, for a pixel and its nearest neighbors, the training samples in a local search window are selected to form the similar patch group by the block matching method. Next, it is factorized by singular value decomposition (SVD), whose left and right orthogonal basis denote local and non-local image features, respectively. The adaptive PCA automatically chooses the local signal subspace dimensionality of the noisy similar patch group in the SVD domain by the refined parallel analysis with Monte Carlo simulation. Thus, image features can be well preserved after dimensionality reduction, and simultaneously the noise is almost eliminated. Then, after the inverse SVD transform, the denoised image is reconstructed from the aggregate filtered patches by the weighted average method. Finally, the collaborative Wiener filtering is used to further remove the noise. The experimental results validate its generality and effectiveness in a wide range of the noisy images. The proposed algorithm not only produces very promising denoising results that outperforms the state-of-the-art methods in most cases, but also adapts to a variety of noise levels.

Multi-focus image fusion based on depth extraction with inhomogeneous diffusion equation

The defocus of imaging can be modeled as a heat diffusion process and represented mathematically by a diffusion equation, where the image blur is corresponded to the diffusion of heat. To improve the quality of observed images, we propose an algorithm of multi-focus image fusion based on the depth extraction. The optical imaging of two multi-focus images is simulated by the heat equations of positive regions, where the scene depth is estimated by the inhomogeneous diffusion equation. An adaptive initialization of image depth estimation is proposed to improve the simulation accuracy of inhomogeneous diffusion process. Image depth is approximated by an iterative solution of the partial differential equation. According to the depth information, the target images are adaptively divided into three types of regions: clear regions, fuzzy regions and transition regions. Finally, the fusion of multi-focus images is achieved by not only extracting the pixels of clear regions but also merging the pixels of transition regions. Theoretical analysis and experimental results show that the proposed algorithm can avoid the blocking artifacts, and outperform the state-of-the-art methods both subjectively and objectively in most cases. HighlightsA novel multi-focus image fusion algorithm is proposed based on depth extraction.Adaptive depth estimation improves the solution of inhomogeneous diffusion equation.The images are divided into three regions according to the depth map.The multi-focus images are fused with different weights in different regions.The proposed method outperforms the state-of-the-art methods in most cases.

Guided image filtering using signal subspace projection

There are various image filtering approaches in computer vision and image processing that are effective for some types of noise, but they invariably make certain assumptions about the properties of the signal and/or noise which lack the generality for diverse image noise reduction. This study describes a novel generalised guided image filtering method with the reference image generated by signal subspace projection (SSP) technique. It adopts refined parallel analysis with Monte Carlo simulations to select the dimensionality of signal subspace in the patch-based noisy images. The noiseless image is reconstructed from the noisy image projected onto the significant eigenimages by component analysis. Training/test image are utilised to determine the relationship between the optimal parameter value and noise deviation that maximises the output peak signal-to-noise ratio (PSNR). The optimal parameters of the proposed algorithm can be automatically selected using noise deviation estimation based on the smallest singular value of the patch-based image by singular value decomposition (SVD). Finally, we present a quantitative and qualitative comparison of the proposed algorithm with the traditional guided filter and other state-of-the-art methods with respect to the choice of the image patch and neighbourhood window sizes.

Hierarchical tone mapping based on image colour appearance model

To solve the problem of low efficiency and poor effect of the current tone mapping methods for the high dynamic range images, the authors propose a hierarchical tone mapping algorithm based on colour appearance model. The discrete Gaussian kernel is used to speed up the bilateral filter. The operation of tone compression in RGB colour space is adopted to correct the colour casts. The extreme values of the pixels are also adjusted in the detail layer. Moreover, after the tone mapping, the colour saturation is enhanced in the image regions of rich details and sharp edges. Experimental results show that the proposed algorithm with less computational cost reduces the halo effect significantly, and achieves the natural colour and the rich details. It outperforms the state-of-the-art methods in terms of visual quality and objective indicators.

Adaptive shock filter for image super-resolution and enhancement

Adaptive shock filter is used to reduce distortion artifacts of upsampled images.Both edge-stopping function term and forward diffusion process term are proposed.The weight of shock filter relies on the gradients of the interpolated image. In view of that image interpolation methods generally tend to produce considerable edge halos, blurring and aliasing artifacts for image super-resolution. A novel image enhancement algorithm based on adaptive shock filter for image super-resolution is proposed to solve this problem. The weight of shock filter can be adjusted adaptively according to the gradients of the interpolated high-resolution image. Thus the diffusion of image edges is suppressed and the artifacts are removed by the forward diffusion. Compared with the traditional shock filter, the proposed algorithm eliminates edge halos and jagged artifacts, whereas the fine image structures are reserved effectively. Theoretical analysis and experimental results demonstrate that the proposed algorithm can achieve better results than the state-of-the-art methods both subjectively and objectively in most cases.

An 8‐channel RF coil array for carotid artery MR imaging in humans at 3 T

PURPOSE Carotid artery diseases due to plaque buildup at the carotid bifurcation are a leading cause of stroke. Accurate plaque quantification and characterization of plaque composition and morphology by magnetic resonance imaging (MRI) is essential to identifying high-risk patients. Difficulties in detecting plaque, which is physically small, and the unique physiological structure of the carotid artery make use of a radio frequency (RF) coil array with high resolution, large longitudinal coverage, and deep penetration ideal for clinical examinations. The goal of this project was to design and fabricate a sensitive RF coil array with sufficient imaging coverage and signal-to-noise ratio (SNR) for carotid artery imaging at 3 T. METHODS Based on clinical requirements and the anatomical structure of the human carotid artery, an 8-channel carotid coil array was designed and fabricated for 3 T MRI of the carotid artery in humans. The performance of the proposed 8-channel carotid coil array was validated through bench tests and MR imaging experiments on a 3 T whole body MRI scanner. Its performance was also compared experimentally to the performance of a commercial 4-channel phased array carotid coil designed by Machnet BV (Machnet BV coil, Roden, Netherlands). RESULTS The 8-channel carotid coil array performed significantly better in imaging the carotid artery than the commercial 4-channel Machnet BV coil in terms of the SNR, coverage, and penetration depth. In parallel imaging, the proposed 8-channel carotid coil array demonstrated a much lower maximum value and average value of the geometry factor in the region of interest. Carotid artery images acquired in vivo using the proposed 8-channel carotid artery coil and the commercial 4-channel Machnet BV coil were also compared, demonstrating the formers potential for clinical diagnosis. CONCLUSIONS Based on the analyses of phantom and in vivo imaging studies, the proposed 8-channel carotid coil array has the potential for use in clinical diagnosis, performing better in terms of SNR, imaging coverage, and penetration depth than the commercial 4-channel carotid artery coil array at 3 T. In future studies, the proposed 8-channel carotid coil array can also serve as an important part of a large-scale multichannel coil array for imaging the whole carotid artery system, including the extracranial and intracranial arteries.

Weighted motion averaging for the registration of multi-view range scans

Multi-view registration is a fundamental but challenging task in 3D reconstruction and robot vision. Although the original motion averaging algorithm has been introduced as an effective means to solve the multi-view registration problem, it does not consider the reliability and accuracy of each relative motion. Accordingly, this paper proposes a novel motion averaging algorithm for multi-view registration. Firstly, it utilizes the pair-wise registration algorithm to estimate the relative motion and overlapping percentage of each scan pair with a certain degree of overlap. With the overlapping percentage available, it views the overlapping percentage as the corresponding weight of each scan pair and proposes the weighted motion averaging algorithm, which can pay more attention to reliable and accurate relative motions. By treating each relative motion distinctively, more accurate registration can be achieved by applying the weighted motion averaging to multi-view range scans. Experimental results demonstrate the superiority of our proposed approach compared with the state-of-the-art methods in terms of accuracy, robustness and efficiency.

Longitudinally Guided Super-Resolution of Neonatal Brain Magnetic Resonance Images

Neonatal magnetic resonance (MR) images typically have low spatial resolution and insufficient tissue contrast. Interpolation methods are commonly used to upsample the images for the subsequent analysis. However, the resulting images are often blurry and susceptible to partial volume effects. In this paper, we propose a novel longitudinally guided super-resolution (SR) algorithm for neonatal images. This is motivated by the fact that anatomical structures evolve slowly and smoothly as the brain develops after birth. We propose a strategy involving longitudinal regularization, similar to bilateral filtering, in combination with low-rank and total variation constraints to solve the ill-posed inverse problem associated with image SR. Experimental results on neonatal MR images demonstrate that the proposed algorithm recovers clear structural details and outperforms state-of-the-art methods both qualitatively and quantitatively.