Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item A time-dependent switching anisotropic diffusion model for denoising and deblurring images(2012) Padikkal, P.; George, S.A conditionally anisotropic diffusion based deblurring and denoising filter is introduced in this paper. This is a time-dependent curvature based model and the steady state can be attained at a faster rate, using the explicit time-marching scheme. The filter switches between isotropic and anisotropic diffusion depending on the local image features. The switching of the filter is controlled by a binary function, which returns either zero or one, based on the underlying local image gradient features. The parameters in the proposed filter can be fine-tuned to get the desired output image. The filter is applied to various kinds of input test images and the response is analyzed. The filter is found to be effective in the reconstruction of partially textured, textured, constant-intensity and color images, as is evident from the results provided. © 2011 Copyright Taylor and Francis Group, LLC.Item Gauss curvature-driven image inpainting for image reconstruction(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2014) Padikkal, P.; George, S.In this paper, we propose a third-order Gauss curvature-driven geometric diffusion Partial Differential Equation for inpainting and reconstructing images. In Gauss curvature-driven diffusion processes, the rate of diffusion is directly proportional to the Gauss curvature value of the level curve. Since the Gauss curvature is the product of principal curvatures, its value become zero when even one of the principal curvatures is zero. Therefore, when Gauss curvature is used as a driving function for diffusion, the evolution preserves some of the meaningful structures with nonzero mean curvature values (viz. curvy edges, corners, etc.). However, the noise features always have nonzero Gauss curvature value and hence the diffusion process effectively removes them. The inpainting property of geometric PDE based on the Gauss curvature is being used in this work for reconstructing lost or degraded information. A filter is proposed to reconstruct the original images from the observed blurred and noisy images along with inpainting the desired image domain. © 2014 Copyright The Chinese Institute of Engineers.Item 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 LtdItem 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.Item 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.