Browsing by Author "Bini, A.A."

Now showing 1 - 20 of 22

A complex diffusion driven approach for removing data-dependent multiplicative noise
(2013) Jidesh, P.; Bini, A.A.
In this paper we propose a second-order non-linear PDE based on the complex diffusion function. The proposed method exhibits better restoration capability of ramp edges in comparison to other second-order methods discussed in the literature. The proposed model is designed for Gamma distributed multiplicative noise which commonly appears in Ultra Sound (US) and Synthetic Aperture Radar (SAR) images. The fidelity/reactive term augmented to the complex diffusive term is derived based on the Bayesian maximum a posteriori probability (MAP) estimator as detailed in Aubert and Ajol ([10]). The regularization parameter is selected based on the noise variance of the image and thus this adaptive method helps in restoring the images at various noise variances without manually fixing the parameter. The results shown in terms of both visual and qualitative measures demonstrate the capability of the model to restore images from their degraded observations. Â© Springer-Verlag 2013.
A Curvature-Driven Image Inpainting Approach for High-Density Impulse Noise Removal
(Springer Verlag, 2014) Padikkal, P.; Bini, A.A.
A PDE-based image inpainting method is proposed in this work for removing high-density impulse noise in images. In this model, the diffusion or inpainting process is driven by the difference curvature of the level curve. The proposed framework has two stages. In the first stage the noisy pixels are detected and they are piped to the second stage. In the second stage, these noisy pixels are inpainted using the information from their neighborhood. The connectivity principle is well realized and the edges and fine details are preserved well by the proposed model. The proposed method is compared (in terms of denoising capability) with the state-of-the-art impulse denoising models. The performance is quantified in terms of statistical quality measures. It is observed that the proposed method is capable of restoring images corrupted with high-density impulse noise (even up to 90 %). The experiments clearly demonstrate the effective restoration capacity of the proposed image inpainting model. © 2014 King Fahd University of Petroleum and Minerals.
A fourth-order Partial Differential Equation model for multiplicative noise removal in images
(IEEE Computer Society, 2013) Bini, A.A.; Bhat, M.S.
In coherent imaging, the sensed images are usually corrupted with multiplicative data dependent noise. Unlike additive noise, the presence of multiplicative noise destroys the information content in the original image to a great extent. In this paper, we propose a new fourth-order Partial Differential Equation (PDE) model with a noise adaptive fidelity term for multiplicative Gamma noise removal under the variational Regularization framework. Variational approaches for multiplicative noise removal generally consist of a maximum a posteriori (MAP) based fidelity term and a Total-Variation (TV) regularization term. However, the second-order TV diffusion approximates the observed images with piecewise constant images, leading to the so-called block effect. The proposed model removes the multiplicative noise effectively and approximates observed images with planar ones making the restored images more natural compared to the second-order diffusion models. The proposed method is compared with the recent state-of-the art methods and the effective restoration capability of the filter is demonstrated experimentally. Â© 2013 IEEE.
A Graph Spectral Approach for Restoring Images Corrupted by Shot-Noise
(Springer Science and Business Media Deutschland GmbH, 2021) Jidesh, P.; Bini, A.A.
Image restoration is a fundamental problem in image processing. Usually, images gets deteriorated while storing or transmitting them. Image restoration is an ill-posed inverse problem, wherein one has to restore the original data with a priori information or assumption regarding the degradation model and its characteristics. The literature is too elaborate for various restorations under different assumptions on the degradation-architecture. This paper introduces a strategy based on graph spectral theory to restore images with non-local filters controlled by a loss function. The non-local similarity-based weight function controls the restoration process resulting in the preservation of local image features considerably well. The parameter controlled adaptive fidelity term helps to re-orient the diffusion to handle data correlated shot-noise following a Poisson distribution, which is pretty common in many medical and telescopic imaging applications. Experimental results are conforming to the fact that the proposed model performs well in restoring images of the different intensity distributions. Â© 2021, Springer Nature Singapore Pte Ltd.
A nonlinear level set model for image deblurring and denoising
(Springer Verlag service@springer.de, 2014) Bini, A.A.; Bhat, M.S.
Image deblurring and denoising are fundamental problems in the field of image processing with numerous applications. This paper presents a new nonlinear Partial Differential Equation (PDE) model based on curve evolution via level sets, for recovering images from their blurry and noisy observations. The proposed method integrates an image deconvolution process and a curve evolution based regularizing process to form a reaction-diffusion PDE. The regularization term in the proposed PDE is a combination of a diffusive image smoothing term and a reactive image enhancement term. The diffusive and reactive terms present in the model lead to effective suppression of noise with sharp restoration of image features. We present several numerical results for image restoration, with synthetic and real degradations and compare it to other state-of-the-art image restoration techniques. The experiments confirm the favorable performance of our method, both visually and in terms of Improvement in Signal-to-Noise-Ratio (ISNR) and Pratt's Figure Of Merit (FOM). © 2013 Springer-Verlag Berlin Heidelberg.
A retinex inspired deep image prior model for despeckling and deblurring of aerial and satellite images using proximal gradient method
(Taylor and Francis Ltd., 2025) Shastry, A.; Bini, A.A.; Padikkal, J.
Unsupervised learning models, particularly in the remote sensing domain, have gained significant attention in recent years. Various degradations in the satellite images, primarily occurring during acquisition, pose a substantial hurdle in obtaining reliable ground truth and extensive training data. The Deep Image Prior model (DIP) addresses these issues by performing restoration tasks using a single image, relying on the implicit regularization inherent in the network architecture. In this paper, we propose a novel approach, integrating the DIP model within the retinex framework to restore aerial and satellite images from the Gamma distributed speckles and linear shift-invariant Gaussian blur along with contrast enhancement using the alternating proximal gradient descent ascent (PGDA) method. Our proposed methodology combines implicit regularization with explicit total variational (TV) regularization, incorporating automated estimation of local regularization parameters. The data-fidelity component in the optimization function is formulated using the Bayesian Maximum A posteriori (MAP) estimate, assuming the speckles follow the Gamma distribution. Demonstration of despeckling and deblurring alone and in addition as a combined task is carried out on aerial and Synthetic Aperture Radar (SAR) images with different resolutions and polarization from various sources. Results obtained are compared with various state-of-the-art despeckling and deblurring models using distinct image quality metrics such as Equivalent Number of Looks (ENL), Contrast to Noise Ratio (CNR), Edge Preserving Index (EPI), Entropy, Global Contrast Factor (GCF), Natural Image Quality Evaluator (NIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Bradley-Terry (B-T) score based on the various factors. The quality of restored images depicted superior performance of the proposed method over the existing models under study. © 2024 Informa UK Limited, trading as Taylor & Francis Group.
A Retinex-Based Variational Model for Enhancement and Restoration of Low-Contrast Remote-Sensed Images Corrupted by Shot Noise
(Institute of Electrical and Electronics Engineers, 2020) Febin, I.P.; Padikkal, P.; Bini, A.A.
Remotely sensed images are widely used in many imaging applications. Images captured under adverse atmospheric conditions lead to degraded images that are contrast deficient and noisy. This study is intended to address these defects of remotely sensed data efficiently. A perceptually inspired variational model is designed based upon the Bayesian framework, powered by the retinex theory. The atmospheric noise or the shot noise (precisely following a Poisson distribution) and contrast inhomogeneity are addressed in this article. The model thus designed is tested and verified both visually and quantitatively using various test data under different statistical measures. The comparative study reveals the efficiency of the model. © 2020 IEEE.
A self-attention driven retinex-based deep image prior model for satellite image restoration
(Elsevier Ltd, 2024) Shastry, A.; Padikkal, J.; George, S.; Bini, A.A.
A self attention driven Deep Image Prior (DIP) framework has been proposed in this work for restoring satellite images corrupted by speckled interference and contrast deficiency. The retinex-based framework incorporated here-in leverages the benefits of DIP approach for image restoration, thus requiring only a single input image, eliminating the need for ground truth or training data. An attention framework is incorporated into the architecture of DIP networks to effectively capture fine textures, enhancing the restoration capability of the model. Two generative networks are employed to obtain the luminance and reflectance maps, with the model's loss functions specifically designed to tackle speckle interference and contrast distortions present in the input. These generated maps eventually reconstruct the enhanced version of the image. Satellite images from different sensors are used to demonstrate and compare the performance of the model. Various state-of-the-art models are evaluated and compared with the proposed strategy using different image quality metrics and statistical tests. The experimental results, incorporating both visual and statistical inferences, demonstrate the superiority and efficiency of the model. Additionally, an ablation analysis is performed to determine optimal regularization parameters, and the significance of integrating attention modules at different architecture layers is also demonstrated. © 2023 Elsevier Ltd
A weighted nuclear norm (WNN)-based retinex DIP framework for restoring aerial and satellite images corrupted by gamma distributed speckle noise
(Springer, 2024) Shastry, A.; Padikkal, J.; George, S.; Bini, A.A.
Restoration and enhancement are crucial preprocessing steps in the satellite domain. Mainly in active remote sensing such as Synthetic Aperture Radar (SAR), the images are more prone to speckle distortions and their reduction is not so trivial. Traditional deep learning models require large training datasets, limiting their applicability. This paper introduces a novel approach that combines the Deep Image Prior (DIP) model with a weighted nuclear norm (WNN) within a variational retinex framework to address these challenges. DIP leverages prior knowledge about noise distribution and works effectively with a single noisy image, eliminating the need for a large number of training images or ground truth. The WNN assigns non-negative weights to singular values, capturing the significance of each value and preserving crucial information during restoration. This approach offers a promising solution for satellite image restoration without relying on huge training data. The proposed method is evaluated through extensive experiments using various image quality metrics, including PSNR, SSIM, ENL, CNR, Entropy, and GCF. The comparative studies provide compelling evidence that the proposed method surpasses existing techniques in effectively restoring and enhancing speckled input images. Furthermore, statistical analysis performed using the Friedman test demonstrates the superior denoising performance of the model. Additionally, an ablation study is conducted to empirically determine the optimal regularization parameters, ensuring the optimal performance of the model. However, the theoretical selection of parameters for achieving optimal results remains an area that requires further exploration. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
An adaptive total variation model with local constraints for denoising partially textured images
(2011) Bini, A.A.; Bhat, M.S.; Jidesh, P.
Denoising algorithms such as Total Variation model modify smooth areas in images into piecewise constant patches and small scale details and textures present in the original image are not preserved satisfactorily by these processes. In this paper, we present an algorithm based on an adaptive Total Variation norm of the gradient of the image, with a family of local constraints for efficient denoising of natural images. In fact, natural images consist of smooth and textured regions. Staircase effect is reduced in smooth areas by using a modified Total Variation functional. The set of local constraints, one for each pixel in the image are able to preserve most of the fine details and textures in the images. Visual and quantitative results of proposed method are presented and are compared with results of existing methods. � 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).
An adaptive total variation model with local constraints for denoising partially textured images
(2011) Bini, A.A.; Bhat, M.S.; Jidesh, P.
Denoising algorithms such as Total Variation model modify smooth areas in images into piecewise constant patches and small scale details and textures present in the original image are not preserved satisfactorily by these processes. In this paper, we present an algorithm based on an adaptive Total Variation norm of the gradient of the image, with a family of local constraints for efficient denoising of natural images. In fact, natural images consist of smooth and textured regions. Staircase effect is reduced in smooth areas by using a modified Total Variation functional. The set of local constraints, one for each pixel in the image are able to preserve most of the fine details and textures in the images. Visual and quantitative results of proposed method are presented and are compared with results of existing methods. Â© 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).
AttentionDIP: attention-based deep image prior model to restore satellite and aerial images from gamma distributed speckle interference
(Springer Science and Business Media Deutschland GmbH, 2024) Shastry, A.; George, S.; Bini, A.A.; Padikkal, J.
Image restoration is an inevitable pre-processing step in most satellite imaging applications. The satellite imaging modality such as Synthetic Aperture Radar (SAR) is prone to speckle distortions due to constructive and destructive interference of the probing signals. Speckles being data correlated and multiplicative, their reduction is not so trivial. Since speckles are not purely noise interventions, a blind reduction process leads to spurious analysis at the later stages. Moreover, the image details are liable to get compromised during such a noise reduction process. An attention-based deep image prior (DIP) model with U-Net architecture has been proposed in this work to carefully address these setbacks. The attention block is used to scale the features extracted from the encoder, and they are concatenated with the features from the decoder to obtain both low- and high-level features. The attention module incorporated in the model helps to extract significant complex structures in SAR images. Further, the DIP model duly respects the noise distribution of speckles while performing the despeckling task. Various synthetic, natural, aerial, and satellite images are subjected to the testing and verification process, and the results obtained are in favor of the proposed model. The quantitative analysis carried out using various statistical metrics in this study also reveals the restoration ability of the proposed method in terms of both despeckling and structure preservation. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.
A complex diffusion driven approach for removing data-dependent multiplicative noise
(2013) Jidesh, P.; Bini, A.A.
In this paper we propose a second-order non-linear PDE based on the complex diffusion function. The proposed method exhibits better restoration capability of ramp edges in comparison to other second-order methods discussed in the literature. The proposed model is designed for Gamma distributed multiplicative noise which commonly appears in Ultra Sound (US) and Synthetic Aperture Radar (SAR) images. The fidelity/reactive term augmented to the complex diffusive term is derived based on the Bayesian maximum a posteriori probability (MAP) estimator as detailed in Aubert and Ajol ([10]). The regularization parameter is selected based on the noise variance of the image and thus this adaptive method helps in restoring the images at various noise variances without manually fixing the parameter. The results shown in terms of both visual and qualitative measures demonstrate the capability of the model to restore images from their degraded observations. � Springer-Verlag 2013.
Despeckling low SNR, low contrast ultrasound images via anisotropic level set diffusion
(Kluwer Academic Publishers, 2014) Bini, A.A.; Bhat, M.S.
Speckle is a form of multiplicative and locally correlated noise which degrades the signal-to-noise ratio (SNR) and contrast resolution of ultrasound images. This paper presents a new anisotropic level set method for despeckling low SNR, low contrast ultrasound images. The coefficient of variation, a speckle-robust edge detector is embedded in the well known geodesic "snakes" model to smooth the image level sets, while preserving and sharpening edges of a speckled image. The method achieves much better speckle suppression and edge preservation compared to the traditional anisotropic diffusion based despeckling filters. In addition, the performance of the filter is less sensitive to the speckle scale of the image and edge contrast parameter, which makes it more suitable for the detection of low contrast features in an ultrasound image. We validate the method using both synthetic and real ultrasound images and quantify the performance improvement over other state-of-the-art algorithms in terms of speckle noise reduction and edge preservation indices. © 2012 Springer Science+Business Media, LLC.
A fourth-order Partial Differential Equation model for multiplicative noise removal in images
(2013) Bini, A.A.; Bhat, M.S.
In coherent imaging, the sensed images are usually corrupted with multiplicative data dependent noise. Unlike additive noise, the presence of multiplicative noise destroys the information content in the original image to a great extent. In this paper, we propose a new fourth-order Partial Differential Equation (PDE) model with a noise adaptive fidelity term for multiplicative Gamma noise removal under the variational Regularization framework. Variational approaches for multiplicative noise removal generally consist of a maximum a posteriori (MAP) based fidelity term and a Total-Variation (TV) regularization term. However, the second-order TV diffusion approximates the observed images with piecewise constant images, leading to the so-called block effect. The proposed model removes the multiplicative noise effectively and approximates observed images with planar ones making the restored images more natural compared to the second-order diffusion models. The proposed method is compared with the recent state-of-the art methods and the effective restoration capability of the filter is demonstrated experimentally. � 2013 IEEE.
Image despeckling and deblurring via regularized complex diffusion
(Springer London, 2017) Padikkal, P.; Bini, A.A.
In this paper an image restoration and enhancement model is being proposed, which is suitable for multiplicative data-dependent speckle noise (whose intensity is Gamma distributed) under linear shift-invariant blurring artifacts. The proposed strategy devises a nonlinear second-order diffusive-reactive model for enhancing and restoring images degraded by the aforementioned scenario. The reactive term is derived based on the Maximum a posteriori (MAP) estimator, to make it adaptive to the noise distribution in the input data. This noise-adaptive reactive term helps to restore and enhance the images under data-correlated noise setup. Unlike the other second-order nonlinear diffusion methods, the proposed solution preserves edges and details and reduces piecewise constant approximation in the homogeneous intensity regions in the course of its evolution. The experimental results demonstrated in this paper duly support the above claims. © 2017, Springer-Verlag London.
Image Restoration Using Adaptive Region-Wise p-Norm Filter with Local Constraints
(World Scientific, 2016) Bini, A.A.; Padikkal, P.
In this work, we introduce a feature adaptive second-order p-norm filter with local constraints for image restoration and texture preservation. The p-norm value of the filter is chosen adaptively between 1 and 2 in a local region based on the regional image characteristics. The filter behaves like a mean curvature motion (MCM) [A. Marquina and S. Osher, SIAM Journal of Scientific Computing 22, 387-405 (2000)] in the regions where the p-norm value is 1 and switches to a Laplacian filter in the rest of the regions (where the p-norm value is 2). The proposed study considerably reduces stair-case effect and effectively removes noise from images while deblurring them. The noise is assumed as Gaussian distributed (with zero mean and variance ?2) and blur is linearly shift invariant (out-of-focus). The filter converges at a faster rate with semi-implicit Crank-Nicholson scheme. The regularization parameter is initialized and updated based on the local image features and therefore this filter preserves edges, structures, textures and fine details present in images very well. The method is applied on different kinds of images with different image characteristics. We show the response of the filter to various kinds of images and numerically quantify the performance in terms of standard statistical measures. © 2016 World Scientific Publishing Company.
Multiple-Coil Magnetic Resonance Image Denoising and Deblurring With Nonlocal Total Bounded Variation
(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2020) Holla Kayyar, K.S.; Padikkal, P.; Bini, A.A.
One of the complex tasks in image restoration is to restore images under data correlated noise contaminations. In real-time medical imaging scenarios, such as Magnetic Resonance (MR), Ultrasound, Computed Tomography(CT) etc, it is observed that, the data of interest is severely degraded with data dependent noise interventions. A Nonlocal Total Bounded Variation (NLTBV) approach is being proposed in this paper to denoise as well as deblur multiple-coil MR images corrupted by non-central Chi distributed noise and linear Gaussian blur. The energy functional for the restoration model is derived by applying the Maximum A Posteriori (MAP) estimator on the Probability Density Function (PDF) of the non-central Chi distribution. The numerical implementation is performed using the split-Bregman iterative scheme to improve the convergence rate. The proposed model is compared with the other state of the art models in terms of both visual and statistical quantifications to demonstrate it's performance. © 2019, © 2019 IETE.
Noise classification and automatic restoration system using non-local regularization frameworks
(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2018) Febin, I.P.; Padikkal, P.; Bini, A.A.
Medical, satellite or microscopic images differ in the imaging techniques used, hence their underlying noise distribution also are different. Most of the restoration methods including regularization models make prior assumptions about the noise to perform an efficient restoration. Here we propose a system that estimates and classifies the noise into different distributions by extracting the relevant features. The system provides information about the noise distribution and then it gets directed into the restoration module where an appropriate regularization method (based on the non-local framework) has been employed to provide an efficient restoration of the data. We have effectively addressed the distortion due to data-dependent noise distributions such as Poisson and Gamma along with data uncorrelated Gaussian noise. The studies have shown a 97.7% accuracy in classifying noise in the test data. Moreover, the system also shows the capability to cater to other popular noise distributions such as Rayleigh, Chi, etc. © 2018, © 2018 The Royal Photographic Society.
Optimizing Hyperparameters in Meta-Learning for Enhanced Image Classification
(Institute of Electrical and Electronics Engineers Inc., 2025) Vincent, A.M.; Padikkal, P.; Bini, A.A.
This paper investigates the significance of hyperparameter optimization in meta-learning for image classification tasks. Despite advancements in deep learning, real-time image classification applications often suffer from data inadequacy. Few-shot learning addresses this challenge by enabling learning from limited samples. Meta-learning, a prominent tool for few-shot learning, learns across multiple classification tasks. We explore different types of meta-learners, with a particular focus on metric-based models. We analyze the potential of hyperparameter optimization techniques, specifically Bayesian optimization and its variants, to enhance the performance of these models. Experimental results on the Omniglot and ImageNet datasets demonstrate that incorporating Bayesian optimization, particularly its evolutionary strategy variant, into meta-learning frameworks leads to improved accuracy compared to settings without hyperparameter optimization. Here, we show that by optimizing hyperparameters for individual tasks rather than using a uniform setting, we achieve notable gains in model performance, underscoring the importance of tailored hyperparameter configurations in meta-learning. © 2013 IEEE.