Corrupted Images Research Articles

Reduced respiratory motion artifacts using structural similarity in fast 2D dynamic contrast enhanced MRI of liver lesions.

The purpose of this work was to improve dynamic contrast enhanced MRI (DCE-MRI) of liver lesions by removing motion corrupted images as identified by a structural similarity (SSIM) algorithm, and to assess the effect of this correction on the pharmacokinetic parameter Ktrans using automatically determined arterial input functions (AIFs). Fifteen patients with colorectal liver metastases were measured twice with a T1 weighted multislice 2D FLASH sequence for DCE-MRI (time resolution 1.2s). AIFs were automatically derived from contrast inflow in the aorta of each patient. Thereafter, SSIM identified motion corrupted images of the liver were removed from the DCE dataset. From this corrected data set Ktrans and its reproducibility were determined. Using the SSIM algorithm a median fraction of 46% (range 37-50%) of the liver images in DCE time series was labeled as motion distorted. Rejection of these images resulted in a significantly lower median Ktrans (p<0.05) and lower coefficient of repeatability of Ktrans in liver metastases compared with an analysis without correction. SSIM correction improves the reproducibility of the DCE-MRI parameter Ktrans in liver metastasis and reduces contamination of Ktrans values of lesions by that of surrounding normal liver tissue.

Designing a compact MRI motion phantom

Abstract Even today, dealing with motion artifacts in magnetic resonance imaging (MRI) is a challenging task. Image corruption due to spontaneous body motion complicates diagnosis. In this work, an MRI phantom for rigid motion is presented. It is used to generate motion-corrupted data, which can serve for evaluation of blind motion compensation algorithms. In contrast to commercially available MRI motion phantoms, the presented setup works on small animal MRI systems. Furthermore, retrospective gating is performed on the data, which can be used as a reference for novel motion compensation approaches. The motion of the signal source can be reconstructed using motor trigger signals and be utilized as the ground truth for motion estimation. The proposed setup results in motion corrected images. Moreover, the importance of preprocessing the MRI raw data, e.g. phase-drift correction, is demonstrated. The gained knowledge can be used to design an MRI phantom for elastic motion.

Fuzzy Logic Decision based Adaptive Directional Weighted Median Filter for Restoring Impulse Corrupted Images

Fuzzy Logic Decision based Adaptive Directional Weighted Median Filter for Restoring Impulse Corrupted Images

Blur Reduction at High Density Impulse Noise

This improved method is a simple, and efficient way to remove impulse noise from highly corrupted digital images. This method has two stages. The first stage is to detect the impulse noise in the image. In this stage, the pixels are divided into two classes (noise free pixels/ noise free pixels) based on only the intensity values. Then, the second stage is to eliminate the impulse noise from the image. In this stage, only the “noise-pixels” are processed. But the “noise-free pixels” are not modified and are copied directly to the output image. The method used gradient based adptive median filter,so that this method adaptively changes the size of the median filter based on the number of the “noise-free pixels” in the neighborhood. For the filtering, the gradian value of every pixel location at (x,y) is calculated. Then the median value can be find out under the consideration of only “noise-free pixels”. In this algorithm for effective noise detection is proposed. The proposed algorithm produces better edge and fine details preservations and reduces blurring at the high density impulse noise. Because of its simplicity, this proposed method is suitable to be implemented in consumer electronics products such as digital television, or digital camera.

Corrupted and occluded face recognition via cooperative sparse representation

In image classification, can sparse representation (SR) associate one test image with all training ones from the correct class, but not associate with any training ones from the incorrect classes? The backward sparse representation (bSR) which contains complementary information in an opposite direction can remedy the imperfect associations discovered by the general forward sparse representation (fSR). Unfortunately, this complementarity between the fSR and the bSR has not been studied in face recognition. There are two key problems to be solved. One is how to produce additional bases for the bSR. In face recognition, there is no other bases than the single test face image itself for the bSR, which results in large reconstruction residual and weak classification capability of the bSR. The other problem is how to deal with the robustness of the bSR to image corruption. In this paper, we introduce a CoSR model, which combines the fSR and the bSR together, into robust face recognition, by proposing two alternative methods to these two key problems: learning bases and unknown faces help to enrich the bases set of the bSR. Thereby, we also propose two improved algorithms of the CoSR for robust face recognition. Our study shows that our CoSR algorithms obtain inspiring and competitive recognition rates, compared with other state-of-the-art algorithms. The bSR with the proposed methods enriching the bases set contributes the most to the robustness of our CoSR algorithm, and unknown faces works better than learned bases. Moreover, since our CoSR model is performed in a subspace with a very low dimensionality, it gains an overwhelming advantage on time consumption over the traditional RSR algorithm in image pixel space. In addition, our study also reveals that the sparsity plays an important role in our CoSR algorithm for face recognition.

Probabilistic decision based filter to remove impulse noise using patch else trimmed median

A new probabilistic decision based filter (PDBF) is presented to remove salt and pepper impulse noise in highly corrupted images. The filter employs two types of estimation techniques for denoising namely trimmed median (TM) and patch else trimmed median (PETM) which is our main contribution in this paper. Depending upon the estimated noise density, the filter utilizes either TM or PETM and hence enhanced outcome of denoising. Simulation results prove that the PDBF has outperformed recently proposed state-of-the-art filters in terms of peak signal to noise ratio (PSNR), structural similarity index (SSIM), image enhancement factor (IEF), mean absolute error (MAE) and visual representation at the noise densities (ND) as high as 95%.

Pixel-level multisensor image fusion based on matrix completion and robust principal component analysis

Acquired digital images are often corrupted by a lack of camera focus, faulty illumination, or missing data. An algorithm is presented for fusion of multiple corrupted images of a scene using the lifting wavelet trans- form. The method employs adaptive fusion arithmetic based on matrix completion and self-adaptive regional variance estimation. Characteristics of the wavelet coefficients are used to adaptively select fusion rules. Robust principal component analysis is applied to low-frequency image components, and regional variance estimation is applied to high-frequency components. Experiments reveal that the method is effective for multifocus, visible-light, and infrared image fusion. Compared with traditional algorithms, the new algorithm not only increases the amount of preserved information and clarity but also improves robustness. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. (DOI: 10.1117/1.JEI.25.1.013007)

A novel learning-based switching median filter for suppression of impulse noise in highly corrupted colour images

A novel switching median filter integrated with a learning-based noise detection method is proposed for suppression of impulse noise in highly corrupted colour images. Noise detection employs a new machine learning algorithm, called margin setting (MS), to detect noise pixels. MS detection is achieved by classifying noise and clean pixels with a decision surface. MS detection yields very high detection accuracy, i.e. a zero miss detection rate and a fairly low over detection rate for a wide range of noise levels. After noise detection, a new filter scheme called the noise-free two-stage (NFTS) filter is triggered. NFTS corrects the noise pixels using the median of the noise-free pixels in two stages. The results of experiments have demonstrated that the MS based NFTS (MSN) filter is superior to the support vector machine and neural network for denoising highly corrupted images, in terms of noise suppression and detail preservation.

On a Gradient-Based Algorithm for Sparse Signal Reconstruction in the Signal/Measurements Domain

Sparse signals can be recovered from a reduced set of samples by using compressive sensing algorithms. In common compressive sensing methods the signal is recovered in the sparsity domain. A method for the reconstruction of sparse signals which reconstructs the missing/unavailable samples/measurements is recently proposed. This method can be efficiently used in signal processing applications where a complete set of signal samples exists. The missing samples are considered as the minimization variables, while the available samples are fixed. Reconstruction of the unavailable signal samples/measurements is preformed using a gradient-based algorithm in the time domain, with an adaptive step. Performance of this algorithm with respect to the step-size and convergence are analyzed and a criterion for the step-size adaptation is proposed in this paper. The step adaptation is based on the gradient direction angles. Illustrative examples and statistical study are presented. Computational efficiency of this algorithm is compared with other two commonly used gradient algorithms that reconstruct signal in the sparsity domain. Uniqueness of the recovered signal is checked using a recently introduced theorem. The algorithm application to the reconstruction of highly corrupted images is presented as well.

Adaptive, Noise-Exclusive and Assessment-Based Fuzzy Switching Median Filter For High Intensity Impulse Noise

The article proposes an adaptive, noise-exclusive and assessment-based fuzzy switching median filter for high intensity impulse noise. The filter adaptively changes the size of sliding window in accordance with noise intensity and noise-exclusive operation is performed only on noise-free pixels. These steps thus preserve the image details effectively. Judicious assessment of the previously restored pixels is made in order to use them in replacing the noisy pixels and further improve the efficiency of filter. With these possibilities, fuzzy switching median filter-based approach is also incorporated for improving the performance. Experimental results justified the efficacy of the proposed fuzzy-based filtering method qualitatively and quantitatively for twelve different highly corrupted noisy images, and showed significant improvement to existing algorithms.

An improved retina-like nonuniformity correction for infrared focal-plane array

The non-uniform response in infrared focal plane array (IRFPA) detectors produces corrupted images with nonuniformity noise. This paper mainly proposes an improved adaptive nonuniformity correction (NUC) method based on the retina-like neural network approach. The main purpose of NUC method is to obtain reliable estimations of gain and offset parameters. In this paper the two correction parameters are updated with two different learning rates respectively for the purpose of updating these two parameters synchronously. And then more accurate estimations of the two correction parameters can be obtained. Again, in order to reduce the ghost artifacts normally introduced by the strong edge effectively, the proposed algorithm employs the non-local means (NLM) method to estimate the desired target value of each detector. The proposed NUC method has been tested by applying it to the IR sequence of frames with simulated nonuniformity noise and real nonuniformity noise, respectively. The performance comparisons are implemented with the well-established scene-based NUC techniques. And the experimental results show the efficiency of the proposed method.

Image classification based on low-rank matrix recovery and Naive Bayes collaborative representation

Most image classification methods require an expensive learning/training phase to gain high performances. But they frequently encounter problems such as overfitting of parameters and scarcity of training data. In this paper, we present a novel learning-free image classification algorithm under the framework of Naive-Bayes Nearest-Neighbor (NBNN) and collaborative representation, where non-negative sparse coding, low-rank matrix recovery and collaborative representation are jointly employed to obtain more robust and discriminative representation. First, instead of using general sparse coding, non-negative sparse coding combined with max pooling is introduced to further reduce information loss. Second, we use the low-rank matrix recovery technique to decompose the training data of the same class into a discriminative low-rank matrix, in which more structurally correlated information is preserved. As for testing images, a low-rank projection matrix is also learned to remove possible image corruptions. Finally, the classification process is implemented by simply comparing the responses over the different bases. Experimental results on several image datasets demonstrate the effectiveness of our method.

Multi-level adaptive switching filters for highly corrupted images

The performance of a switching filter is highly dependent on its detection accuracy. Inspired by adaptive median filter methodology, this paper proposes a multi-level adaptive switching filter (MASF) for the recovery of highly corrupted images. In particular, the adaptive technique is employed in all the detective, edge-preserving and restorative stages in order to improve noise discrimination and suppression simultaneously. Most critical design parameters in the proposed algorithm, e.g., the limit of window-expansion size and the noise range, are self-adaptive so as to retain simple implementation and high computational efficiency. Furthermore, several effective modifications on both stages of the MASF, such as the convergence factor, switching initialization and spatial adaptive weighting, are also introduced in order to provide better and more robust results. Monte-Carlo simulations show that the MASF outperforms many existing state-of-the-art algorithms in terms of both visual and quantitative results.

Content adaptive video denoising based on human visual perception

In this paper, we propose content adaptive denoising in highly corrupted videos based on human visual perception. We introduce the human visual perception in video denoising to achieve good performance. In general, smooth regions corrupted by noise are much more annoying to human observers than complex regions. Moreover, human eyes are more interested in complex regions with image details and more sensitive to luminance than chrominance. Based on the human visual perception, we perform perceptual video denoising to effectively preserve image details and remove annoying noise. To successfully remove noise and recover the image details, we extend nonlocal mean filtering to the spatiotemporal domain. With the guidance of content adaptive segmentation and motion detection, we conduct content adaptive filtering in the YUV color space to consider context in images and obtain perceptually pleasant results. Extensive experiments on various video sequences demonstrate that the proposed method reconstructs natural-looking results even in highly corrupted images and achieves good performance in terms of both visual quality and quantitative measures.

Perceptual grouping by tensor voting: a comparative survey of recent approaches

Tensor voting is a computational framework that addresses the problem of perceptual organisation. It was designed to convey human perception principles into a unified framework that can be adapted to extract visually salient elements from possibly noisy or corrupted images. The original formulation featured some concerns that made it difficult or impractical to be applied directly. Therefore, several partial or total theoretical reformulations or augmentations have been proposed. These almost parallel publication were presented in different directions, with different priorities and even in a different notation. Thus, the authors observed the need for a coherent description and comparison of the different proposals. This work, after describing the original approach of tensor voting, reviews and explains a number of high impact theoretical modifications in a self‐contained manner and including possible future directions of work. The authors have selected and organised a number of formulations and unified the way the problem is addressed across the different proposals. The aim of this study is to contribute with a modern comprehensive source of information on the theoretical aspects of tensor voting.

Sparse representation-based robust face recognition by graph regularized low-rank sparse representation recovery

This paper proposes a graph regularized low-rank sparse representation recovery (GLRSRR) method for sparse representation-based robust face recognition, in which both the training and test samples might be corrupted because of illumination variations, pose changes, and occlusions. On the one hand, GLRSRR imposes both the lowest-rank and sparsest constraints on the representation matrix of the training samples, which makes the recovered clean training samples discriminative while maintaining the global structure of data. Simultaneously, GLRSRR explicitly encodes the local structure information of data and the discriminative information of different classes by incorporating a graph regularization term, which further improves the discriminative ability of the recovered clean training samples for sparse representation. As a result, a test sample is compactly represented by more clean training samples from the correct class. On the other hand, since the error matrix obtained by GLRSRR can accurately and intuitively characterize the corruption and occlusion of face image, it can be used as occlusion dictionary for sparse representation. This will bring more accurate representations of the corrupted test samples. The experimental results on several benchmark face image databases manifest the effectiveness and robustness of GLRSRR.

An Efficient Approach for Removal of Impulse Noise from Highly Corrupted Images

In this paper, a method based on adaptive fuzzy filter is used to denoise image corrupted by impulse noise. The algorithm is proposed for restoration of grayscale as well as color images which are highly corrupted by salt and pepper noise. The algorithm detects level of corruption for each pixel using triangular fuzzy membership function to ensure the replacement of noisy pixels based on degree of corruption. Besides providing ease of computation here we use fully adaptive and automatically adjustable threshold value. Final result shows better performance in the impulse noise reduction over standard images relative to the conventional median filtering approach in terms of both noise reduction and fine detail preservation.

Bayesian Image Restoration for Poisson Corrupted Image Using a Latent Variational Method with Gaussian MRF

Bayesian Image Restoration for Poisson Corrupted Image Using a Latent Variational Method with Gaussian MRF

Bayesian Image Restoration for Poisson Corrupted Image Using a Latent Variational Method with Gaussian MRF

We treat an image restoration problem with a Poisson noise chan- nel using a Bayesian framework. The Poisson randomness might be appeared in observation of low contrast object in the field of imaging. The noise observation is often hard to treat in a theo- retical analysis. In our formulation, we interpret the observation through the Poisson noise channel as a likelihood, and evaluate the bound of it with a Gaussian function using a latent variable method. We then introduce a Gaussian Markov random field (GMRF) as the prior for the Bayesian approach, and derive the posterior as a Gaussian distribution. The latent parameters in the likelihood and the hyperparameter in the GMRF prior could be treated as hid- den parameters, so that, we propose an algorithm to infer them in the expectation maximization (EM) framework using loopy belief propagation(LBP). We confirm the ability of our algorithm in the computer simulation, and compare it with the results of other im- age restoration frameworks.

Three-dimensional brain magnetic resonance imaging segmentation via knowledge-driven decision theory.

Brain tissue segmentation on magnetic resonance (MR) imaging is a difficult task because of significant intensity overlap between the tissue classes. We present a new knowledge-driven decision theory (KDT) approach that incorporates prior information of the relative extents of intensity overlap between tissue class pairs for volumetric MR tissue segmentation. The proposed approach better handles intensity overlap between tissues without explicitly employing methods for removal of MR image corruptions (such as bias field). Adaptive tissue class priors are employed that combine probabilistic atlas maps with spatial contextual information obtained from Markov random fields to guide tissue segmentation. The energy function is minimized using a variational level-set-based framework, which has shown great promise for MR image analysis. We evaluate the proposed method on two well-established real MR datasets with expert ground-truth segmentations and compare our approach against existing segmentation methods. KDT has low-computational complexity and shows better segmentation performance than other segmentation methods evaluated using these MR datasets.