Quaternion‐Based Image Restoration via Saturation‐Value Total Variation and Pseudo‐Norm Regularization

Blurring facial images can significantly degrade the performance of face recognition and video surveillance applications. Therefore, an effective image restoration method is essential to address this issue. However, existing methods struggle with varying levels of blur severity, limiting their effectiveness. This study proposes a facial image restoration approach that integrates blur severity classification using a Convolutional Neural Network (CNN) with a U-Net-based deblurring model to overcome these challenges. This method ensures that each blurred image is processed using the most suiTable deblurring model, optimizing the restoration process. The dataset used in this study is Flickr-Faces-HQ (FFHQ), to which a Gaussian blur is applied and categorized into five levels: very low, low, medium, high, and very high. They employ the Peak Signal-to-Noise Ratio (PSNR) and the Structural Similarity Index Measure (SSIM) as quantitative metrics to evaluate the model's performance. Experimental results show that the proposed method consistently outperforms fixed kernel size and multi-kernel size deblurring approaches across all blur severities. Specifically, our method achieves a PSNR of 40.001 dB for very low blur severity and an SSIM of 0.990. For low severity, it attains a PSNR of 31.104 dB and an SSIM of 0.946. For medium severity, the results are 27.995 dB (PSNR) and 0.874 (SSIM). At high severity, our model achieves a PSNR of 28.896 dB and an SSIM of 0.855. Finally, for very high severity, the PSNR drops to 26.566 dB, with an SSIM of 0.812. These results demonstrate the effectiveness of the proposed method in enhancing image clarity across different blur levels while preserving facial details. This research contributes to the development of more adaptive and efficient image restoration techniques, particularly for applications that require high-quality facial images, such as face recognition and video surveillance.

Removal of impulse noise from color images is a stringent job in the arena of image processing. Impulse noise is fundamental of two types: Salt and pepper noise (SAPN) and Random valued impulse noise (RVIN). The key challenge in impulse noise removal from color images lies in tackling out the randomness in the noise pattern and in handling multiple color channels efficiently. Over the years, several filters have been designed to remove impulse noise from color images, but still, the researchers face a stringent challenge in designing a filter effective at high noise densities. In this study, a combination of K-means clustering-based detection followed by a minimum distance-based approach for removal is taken for high-density impulse noise removal from color images. In the detection phase, K-means clustering is applied on combined data consisting of elements from designated 5 × 5 windows of all the planes from RGB color images to segregate noisy and non-noisy elements. In the removal phase, noisy pixels are replaced by taking the average of medians of all non-noisy pixels and non-noisy pixels under 7 × 7 windows residing at least Manhattan distance from the inspected noisy pixel. Performance of the proposed method is evaluated and compared up against the latest filters, on the basis of well-known metrices, such as Peak signal to noise ratio (PSNR) and Structural similarity index measurement (SSIM). Based on these comparisons, the proposed filter is found superior than the compared filters in removing impulse noise at high noise densities.

Multiclass SVM based adaptive filter for removal of high density impulse noise from color images

This paper investigates the application of unsupervised learning methods for computed tomography reconstruction. To motivate our work, we review several existing priors, namely the truncated Gaussian prior, the prior, the total variation prior, and the deep image prior (DIP). We find that DIP outperforms the other three priors in terms of representational capability and visual performance. However, the performance of DIP deteriorates when the number of iterations exceeds a certain threshold due to overfitting. To address this issue, we propose a novel method (MCDIP‐ADMM) based on multi‐code deep image prior (MCDIP) and plug‐and‐play alternative direction method of multipliers (ADMM). Specifically, MCDIP utilizes multiple latent codes to generate a series of feature maps at an intermediate layer within a generator model. These maps are then composed with trainable weights, representing the complete image prior. Experimental results demonstrate the superior performance of the proposed MCDIP‐ADMM compared to three existing competitors. In the case of parallel beam projection with Gaussian noise, MCDIP‐ADMM achieves an average improvement of 4.3 dB over DIP, 1.7 dB over ADMM DIP‐weighted total variation (WTV) and 1.2 dB over PnP‐DIP in terms of peak‐signal‐to‐noise ratio (PSNR). Similarly, for fan‐beam projection with Poisson noise, MCDIP‐ADMM achieves an average improvement of 3.09 dB over DIP, 1.86 dB over ADMM DIP‐WTV and 0.84 dB over PnP‐DIP in terms of PSNR.

In the process of signal and image acquisition and transmission, there is not only the additive white Gaussian noise interference, but also the non-Gaussian noise interference. The performance of a standard reconstruction algorithm, known as compressed sensing, can be significantly reduced if it is used to recover the signal affected by non-Gaussian noise. In this paper, LpLq-ADMM algorithm $(p \in(0,2), q \in(0,1))$ based on alternating direction method of multipliers is proposed to improve the reconstruction accuracy and the robustness of signal and image restoration in impulsive SαS (symmetric α-stable) noise. Lp-norm is used as the loss function term to enhance the data restoration ability in SαS noise and Lq-norm is used as the generalized non-convex penalty term to guarantee the sparsity of the signal. In order to efficiently solve the cost function model with minimum non-convex and nonsmooth, reduce the computational complexity of the objective function and improve the processing ability of high-dimensional data, in this paper, the alternating direction method of multipliers (ADMM) is used to solve the cost function model. The appropriate p and q values are selected via numerical simulation experiments to achieve the optimal reconstruction accuracy and robustness of sparse signals in SαS noise. The reconstruction probability of sparse signals and image recovery performance are analyzed under the optimal p and q values. The simulation results show that LpLq-ADMM algorithm has great noise suppression ability to SαS noise, and its Peak Signal to Noise Ratio (PSNR) and signal recovery probability is higher than other recovery algorithms.

Image quality measurements are valuable tools, crucial for most image processing applications, and used in particular to assess and compare the image restoration (IR) quality. The objective of this work is to investigate the potential of such measures when used as cost functions (integrated in the global criterion) to enhance the restoration performance. In this paper, the proposed approach uses the Structural SIMilarity (SSIM) index measure which is one of the most appropriate measures as it is inspired from the human visual system (HVS) and relatively simple to compute. For the composite criterion optimization, after initializing the algorithm by the alternating direction method of multipliers (ADMM), a gradient descent (GD) technique is used to minimize the global cost function. Finally, simulations are conducted to investigate the contexts in which such quality measures might lead to the desired IR improvement.

In this paper we proposed an algorithm for the visibility restoration of color rainy images. Rain drops affect the visual impact on image so that the visibility and intensity of the captured images are very low. We use a L 0 gradient minimization technique for removing the rain pixels. L 0 gradient minimization technique globally control the non zero gradient, so that low amplitude and insignificant detail are diminished but salient edges of the images are preserved. First we apply this refining illumination techniques on our rainy image for removing the rain and Secondly we apply a bilateral filtering for smoothing the color image for human perception. The quantitative results of proposed algorithm and other existing rainy algorithms for color rainy images are obtained in terms peak to peak signal to noise ratio (PSNR), universal image quality index(UIQI) and structure similarity index measurement (SSIM) and on different color rainy images from databases. The visual quality of the proposed algorithm also better than other existing rainy algorithms. Finally, the simulation result shows that the proposed algorithm is highly effective and efficient for visibility restoration of rainy images.

Introduction[18F]fluorodeoxyglucose ([18F]FDG) brain PET is used clinically to detect small areas of decreased uptake associated with epileptogenic lesions, e.g., Focal Cortical Dysplasias (FCD) but its performance is limited due to spatial resolution and low contrast. We aimed to develop a deep learning-based PET image enhancement method using simulated PET to improve lesion visualization.MethodsWe created 210 numerical brain phantoms (MRI segmented into 9 regions) and assigned 10 different plausible activity values (e.g., GM/WM ratios) resulting in 2100 ground truth high quality (GT-HQ) PET phantoms. With a validated Monte-Carlo PET simulator, we then created 2100 simulated standard quality (S-SQ) [18F]FDG scans. We trained a ResNet on 80% of this dataset (10% used for validation) to learn the mapping between S-SQ and GT-HQ PET, outputting a predicted HQ (P-HQ) PET. For the remaining 10%, we assessed Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Squared Error (RMSE) against GT-HQ PET. For GM and WM, we computed recovery coefficients (RC) and coefficient of variation (COV). We also created lesioned GT-HQ phantoms, S-SQ PET and P-HQ PET with simulated small hypometabolic lesions characteristic of FCDs. We evaluated lesion detectability on S-SQ and P-HQ PET both visually and measuring the Relative Lesion Activity (RLA, measured activity in the reduced-activity ROI over the standard-activity ROI). Lastly, we applied our previously trained ResNet on 10 clinical epilepsy PETs to predict the corresponding HQ-PET and assessed image quality and confidence metrics.ResultsCompared to S-SQ PET, P-HQ PET improved PNSR, SSIM and RMSE; significatively improved GM RCs (from 0.29 ± 0.03 to 0.79 ± 0.04) and WM RCs (from 0.49 ± 0.03 to 1 ± 0.05); mean COVs were not statistically different. Visual lesion detection improved from 38 to 75%, with average RLA decreasing from 0.83 ± 0.08 to 0.67 ± 0.14. Visual quality of P-HQ clinical PET improved as well as reader confidence.ConclusionP-HQ PET showed improved image quality compared to S-SQ PET across several objective quantitative metrics and increased detectability of simulated lesions. In addition, the model generalized to clinical data. Further evaluation is required to study generalization of our method and to assess clinical performance in larger cohorts.

In this study, we propose a CNN-GAN-based real-time processing technique for filtering images of underwater cables used in power systems. This addresses the excessive interference impurities that are frequently observed in images captured by remotely operated vehicles (ROVs). The process begins with the input of the original image into the convolutional neural network (CNN). Subsequently, the training outcomes, which serve as input parameters for the generative adversarial network (GAN), facilitate the filtering process. The system also calculates both the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR), performing model updates via backward propagation. This technique utilizes deep learning technologies to achieve rapid, real-time filtering of underwater cable images. The experimental results reveal that the loss function of the CNN reaches 0.16 with an accuracy of 97.5%, while the loss function of the adversarial GAN network approaches 0.05. Compared with traditional methods such as DDN, JORDOR, RESCAN, and PRENet, the proposed CNN-GAN algorithm exhibits superior performance, as evidenced by the higher PSNR and SSIM values. Specifically, for clear water images, the PSNR reaches 29.86 dB and the SSIM is 0.9045. For severely polluted images, the PSNR is 28.67 dB and the SSIM is 0.8965, while for unevenly illuminated images, the PSNR and SSIM values are 24.37 dB and 0.88, respectively. These enhancements significantly benefit the monitoring and maintenance of power systems.

Aim: Image is the most powerful tool to analyze the information. Sometimes the captured image gets affected with blur and noise in the environment, which degrades the quality of the image. Image restoration is a technique in image processing where the degraded image can be restored or recovered to its nearest original image. Materials and Methods: In this research Lucy-Richardson algorithm is used for restoring blurred and noisy images using MATLAB software. And the proposed work is compared with Wiener filter, and the sample size for each group is 30. Results: The performance was compared based on three parameters, Power Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Normalized Correlation (NC). High values of PSNR, SSIM and NC indicate the better performance of restoration algorithms. Lucy-Richardson provides a mean PSNR of 10.4086db, mean SSIM of 0.4173%, and NC of 0.7433% and Wiener filter provides a mean PSNR of 6.3979db, SSIM of 0.3016%, NC of 0.3276%. Conclusion: Based on the experimental results and statistical analysis using independent sample T test, image restoration using Lucy-Richardson algorithm significantly performs better than Wiener filter on restoring the degraded image with PSNR (P<0.001) and SSIM (P<0.001).

Image repair often has errors in filling. An exemplar-based technique has the advantage of filling texture and structure simultaneously, but there exist some problems with this, such as not considering the overall situation of inpainting, the unreasonable calculation of priority, and random selection when there are multiple candidate patches. In view of these situations, this paper proposes a method of screen window propagating where the upper layer guides the lower layer inpainting from the top layer by means of multiple resolution decomposition. Screen window propagating aims to constrain the inpainting of the lower layer and maintain the overall profile. Improving the priority calculation using the upper repair result can lead to getting a better repair order. When there is more than one candidate patch, the structural similarity index measure (SSIM) is used to obtain the best candidate patch. We consider four cases of rotation and inversion when looking for the best exemplar. The experiments show that our method can obtain more satisfactory results than other methods based on subjective and objective indicators, such as peak signal-to-noise ratio (PSNR), SSIM, and feature similarity index measurement. Screen window propagating for image inpainting aims toward image restoration. Whole contours are preserved and the lower layer can utilize more upper layer information. Our method considers information from the whole and its parts.

The rapid accumulation of marine debris poses a substantial threat to ocean ecosystems, specifically the degradation of plastics, composite materials, and metals. Effective detection and classification of debris by material type are essential during the waste management and material recycling process. However, the underwater debris detection is often hampered by low contrast, color distortion, and noise in underwater imagery. Different deep learning models are proposed in the literature for debris detection, however most of them suffered with limitations in real time implementation complexity and inaccurate instance segmentation. This work proposes an adaptive hybrid lightweight Mask R-CNN system including image augmentation, object identification, and real-time instance segmentation to handle these issues. The preprocessed images are feed to the lightweight mask RCNN model for the object detection and segmentation. The proposed model uses an upgraded Region Proposal Network (RPN) for exact localization of underwater trash and MobileNetV3 as a lightweight backbone for effective feature representation. The model uses data augmentation methods including contrast correction, flipping, and blurring to improve robustness; the model also trained on the proprietary underwater debris datasets. Compared to the conventional approaches, performance evaluation metrics employing Mean Average Precision (mAP), Structural Similarity Index Measure (SSIM), Intersection over Union (IoU), and Peak Signal to Noise Ratio (PSNR) shows better accuracy. Furthermore, the model performs real-time computing at 30 FPS, which makes it highly suitable for usage in real-time operations.

Quaternion weighted Schatten [formula omitted]-norm minimization for color image restoration with convergence guarantee

This paper outlines a novel procedure to restore digital color images using models that vary within a given image. Linear models are used and inter-component correlation is included in the models. A maximum likelihood identification technique in conjunction with a Kalman filter determines model parameters and restores the image. The algoritlim is made adaptive by segmenting the image into regions in which the models are assumed stationary. The result is an efficient adaptive parameter identification/image restoration of color images.

In the last decades, unsupervised deep learning based methods have caught researchers' attention, since in many real applications, such as medical imaging, collecting a large amount of training examples is not always feasible. Moreover, the construction of a good training set is time consuming and hard because the selected data have to be enough representative for the task. In this paper, we focus on the Deep Image Prior (DIP) framework and we propose to combine it with a space-variant Total Variation regularizer with an automatic estimation of the local regularization parameters. Differently from other existing approaches, we solve the arising minimization problem via the flexible Alternating Direction Method of Multipliers (ADMM). Furthermore, we provide a specific implementation also for the standard isotropic Total Variation. The promising performances of the proposed approach, in terms of PSNR and SSIM values, are addressed through several experiments on simulated as well as real natural and medical corrupted images.