Hasil untuk "eess.IV"

Wojciech Górny, Michał Łasica, Alexandros Matsoukas

We propose a new image denoising model based on a variable-growth total variation regularization of double-phase type with adaptive weight. It is designed to reduce staircasing with respect to the classical Rudin--Osher--Fatemi model, while preserving the edges of the image in a similar fashion. We implement the model and test its performance on synthetic and natural images in 1D and 2D over a range of noise levels.

Sergey Krivenko, Alexander Zemliachenko, Vladimir Lukin et al.

The paper presents an automated software tool for lossy compression of grayscale images. Its structure and facilities are described. The tool allows compressing images by different coders according to a chosen metric from an available set of quality metrics with providing a preset metric value. Examples of the tool application to several practical situations are represented.

Yicheng Zhu

Tracking surgical modifications based on endoscopic videos is technically feasible and of great clinical advantages; however, it still remains challenging. This report presents a modular pipeline to divide and conquer the clinical challenges in the process. The pipeline integrates frame selection, depth estimation, and 3D reconstruction components, allowing for flexibility and adaptability in incorporating new methods. Recent advancements, including the integration of Depth-Anything V2 and EndoDAC for depth estimation, as well as improvements in the Iterative Closest Point (ICP) alignment process, are detailed. Experiments conducted on the Hamlyn dataset demonstrate the effectiveness of the integrated methods. System capability and limitations are both discussed.

Arian Azarang, Nasser Kehtarnavaz

This paper presents a generative model method for multispectral image fusion in remote sensing which is trained without supervision. This method eases the supervision of learning and it also considers a multi-objective loss function to achieve image fusion. The loss function incorporates both spectral and spatial distortions. Two discriminators are designed to minimize the spectral and spatial distortions of the generative output. Extensive experimentations are conducted using three public domain datasets. The comparison results across four reduced-resolution and three full-resolution objective metrics show the superiority of the developed method over several recently developed methods.

Joaquin Royo-Miquel, Silvia Tolu, Frederik E. T. Schöller et al.

The paper proposes a method to convert a deep learning object detector into an equivalent spiking neural network. The aim is to provide a conversion framework that is not constrained to shallow network structures and classification problems as in state-of-the-art conversion libraries. The results show that models of higher complexity, such as the RetinaNet object detector, can be converted with limited loss in performance.

Peijian Ding

While Computerized Tomography (CT) images can help detect disease such as Covid-19, regular CT machines are large and expensive. Cheaper and more portable machines suffer from errors in geometry acquisition that downgrades CT image quality. The errors in geometry can be represented with parameters in the mathematical model for image reconstruction. To obtain a good image, we formulate a nonlinear least squares problem that simultaneously reconstructs the image and corrects for errors in the geometry parameters. We develop an accelerated alternating minimization scheme to reconstruct the image and geometry parameters.

Evan Scullion, Soren Nelson, Rajesh Menon

We demonstrate optics-free imaging of complex QR-codes using a bare image sensor and a trained artificial neural network (ANN). The ANN is trained to interpret the raw sensor data for human visualization. The image sensor is placed at a specified gap from the QR code. We studied the robustness of our approach by experimentally testing the output of the ANNs with system perturbations of this gap, and the translational and rotational alignments of the QR code to the image sensor. Our demonstration opens us the possibility of using completely optics-free cameras for application-specific imaging of complex, non-sparse objects.

Yuliana Jiménez-Gaona, María José Rodríguez-Álvarez, Vasudevan Lakshminarayanan

This paper provides a critical review of the literature on deep learning applications in breast tumor diagnosis using ultrasound and mammography images. It also summarizes recent advances in computer-aided diagnosis (CAD) systems, which make use of new deep learning methods to automatically recognize images and improve the accuracy of diagnosis made by radiologists. This review is based upon published literature in the past decade (January 2010 January 2020). The main findings in the classification process reveal that new DL-CAD methods are useful and effective screening tools for breast cancer, thus reducing the need for manual feature extraction. The breast tumor research community can utilize this survey as a basis for their current and future studies.

Manu Francis, Muhammed Tarek, Mark Pickering et al.

Single Photon Emission Computed Tomography (SPECT) is one of the nuclear medicine imaging modalities used for functional analysis of animal and human organs. Gamma rays emitted from the scanned body are filtered with collimators and detected by the SPECT head that is composed of an array of gamma detectors. The conventional reconstruction algorithms do not deem the uncertainty level that is associated with the field of view of SPECT collimators. In this paper, we incorporate the probabilistic programming approach for SPECT image reconstruction. No-U-Turn Sampler (NUTS) is used to estimate the scanned object system by considering uncertainty. The obtained results indicate that the presented work in 3D SPECT image reconstruction surpassed over the conventional reconstruction methods in terms of generating uncertainty information. However, the reconstruction time needs to be improved further for phantom sizes of 128x128x128 voxels and higher.

Marta Lazzaretti, Luca Calatroni, Claudio Estatico

We propose a continuous non-convex variational model for Single Molecule Localisation Microscopy (SMLM) super-resolution in order to overcome light diffraction barriers. Namely, we consider a variation of the Continuous Exact $\ell_0$ (CEL0) penalty recently introduced to relax the $\ell_2-\ell_0$ problem where a weighted-$\ell_2$ data fidelity is considered to model signal-dependent Poisson noise. For the numerical solution of the associated minimisation problem, we consider an iterative reweighted $\ell_1$ (IRL1) strategy for which we detail efficient parameter computation strategies. We report qualitative and quantitative molecule localisation results showing that the proposed weighted-CEL0 (wCEL0) model improves the results obtained by CEL0 and state-of-the art deep-learning approaches for the high-density SMLM ISBI 2013 dataset.

Aaron Defazio, Tullie Murrell, Michael P. Recht

MRI images reconstructed from sub-sampled Cartesian data using deep learning techniques often show a characteristic banding (sometimes described as streaking), which is particularly strong in low signal-to-noise regions of the reconstructed image. In this work, we propose the use of an adversarial loss that penalizes banding structures without requiring any human annotation. Our technique greatly reduces the appearance of banding, without requiring any additional computation or post-processing at reconstruction time. We report the results of a blind comparison against a strong baseline by a group of expert evaluators (board-certified radiologists), where our approach is ranked superior at banding removal with no statistically significant loss of detail.

Sayantan Bhadra, Weimin Zhou, Mark A. Anastasio

Medical image reconstruction is typically an ill-posed inverse problem. In order to address such ill-posed problems, the prior distribution of the sought after object property is usually incorporated by means of some sparsity-promoting regularization. Recently, prior distributions for images estimated using generative adversarial networks (GANs) have shown great promise in regularizing some of these image reconstruction problems. In this work, we apply an image-adaptive GAN-based reconstruction method (IAGAN) to reconstruct high fidelity images from incomplete medical imaging data. It is observed that the IAGAN method can potentially recover fine structures in the object that are relevant for medical diagnosis but may be oversmoothed in reconstructions with traditional sparsity-promoting regularization.

EL-Hachemi Guerrout, Ramdane Mahiou, Dominique Michelucci et al.

Segmentation of medical images is an essential part in the process of diagnostics. Physicians require an automatic, robust and valid results. Hidden Markov Random Fields (HMRF) provide powerful model. This latter models the segmentation problem as the minimization of an energy function. Cuckoo search (CS) algorithm is one of the recent nature-inspired meta-heuristic algorithms. It has shown its efficiency in many engineering optimization problems. In this paper, we use three cuckoo search algorithm to achieve medical image segmentation.

Zhengxue Cheng, Heming Sun, Masaru Takeuchi et al.

In this paper, we provide a detailed description on our approach designed for CVPR 2019 Workshop and Challenge on Learned Image Compression (CLIC). Our approach mainly consists of two proposals, i.e. deep residual learning for image compression and sub-pixel convolution as up-sampling operations. Experimental results have indicated that our approaches, Kattolab, Kattolabv2 and KattolabSSIM, achieve 0.972 in MS-SSIM at the rate constraint of 0.15bpp with moderate complexity during the validation phase.

Andreas Bock, Alexis Arnaudon, Colin Cotter

We present a framework for shape matching in computational anatomy allowing users control of the degree to which the matching is diffeomorphic. This control is given as a function defined over the image and parameterises the template deformation. By modelling localised template deformation we have a mathematical description of growth only in specified parts of an image. The location can either be specified from prior knowledge of the growth location or learned from data. For simplicity, we consider landmark matching and infer the distribution of a finite dimensional parameterisation of the control via Markov chain Monte Carlo. Preliminary numerical results are shown and future paths of investigation are laid out. Well-posedness of this new problem is studied together with an analysis of the associated geodesic equations.

Liang Zhao, Brendan Odigwe, Susan Lessner et al.

We report an object tracking algorithm that combines geometrical constraints, thresholding, and motion detection for tracking of the descending aorta and the network of major arteries that branch from the aorta including the iliac and femoral arteries. Using our automated identification and analysis, arterial system was identified with more than 85% success when compared to human annotation. Furthermore, the reported automated system is capable of producing a stenosis profile, and a calcification score similar to the Agatston score. The use of stenosis and calcification profiles will lead to the development of better-informed diagnostic and prognostic tools.

Wen-Kai Yu

Structured-light three-dimensional (3D) imaging can achieve 3D shape of a stationary object via one or more pixelated array cameras with phase-shifting illumination. In order to extend 3D imaging to moving scenarios, we propose a 3D imaging method with double projection of a single-frame modulated light pattern and a sampling pattern. It can continuously image the moving 3D scene by making multi-pixel detector axial flat brush scan along the motion axis. Utilizing spatial multiplexing for multiple single-pixel imaging, each single-pixel does not need to keep staring at some part of the object, avoiding motion blur problem. The performance of our method has been demonstrated by numerical simulations. Given this, we believe that the technique paves the way to practical applications including product line 3D monitoring.

Rémi Cogranne

Identifying the quality factor of JPEG images is very useful for applications in digital image forensics. Though several command-line tools exist and are used in widely used software such as \emph{GIMP} (GNU Image Manipulation Program), the well-known image editing software, or the \emph{ImageMagick} suite, we have found that those may provide inaccurate or even wrong results. This paper presents a simple method for determining the exact quality factor of a JPEG image from its quantization tables. The method is presented briefly and a sample program, written in Unix/Linux Shell bash language is provided.

Ardymulya Iswardani, Wahyu Hidayat

Abstract PURPOSES this study aims to perform microcalsification detection by performing image enhancement in mammography image by using transformation of negative image and histogram equalization. image mammography with .pgm format changed to. jpg format then processed into negative image result then processed again using histogram equalization. the results of the image enhancement process using negative image techniques and equalization histograms are compared and validated with MSE and PSNR on each mammographic image. CONCLUSION: Image enhancement process on mammography image can be done, however there are only some image that have improved quality, this affected by threshold usage, which have important role to get better visualization on mammographic image. Keywords-component; Image enhancement, image negative, histogram equalization, mammographic, breast cancer

Yves Capdeboscq, Hrand Mamigonians, Aslam Sulaimalebbe et al.

This paper describes a coplanar non invasive non destructive capacitive imaging device. We first introduce a mathematical model for its output, and discuss some of its theoretical capabilities. We show that the data obtained from this device can be interpreted as a weighted Radon transform of the electrical permittivity of the measured object near its surface. Image reconstructions from experimental data provide good surface resolution as well as short depth imaging, making the apparatus a $2d+1$ imager. The quality of the images leads us to expect that excellent results can be delivered by \emph{ad-hoc} optimized inversion formulas. There are also interesting, yet unexplored, theoretical questions on imaging that this sensor will allow to test.