Read and Download eBook Full
Author:
Publisher:
Published: 2011
Total Pages: 176
ISBN-13:
DOWNLOAD EBOOKIn addition, the two proposed methods can be combined to create the reconstruction robust to both Gaussian and impulsive noise.
Author: Ming Yan
Publisher:
Published: 2012
Total Pages: 115
ISBN-13:
DOWNLOAD EBOOKMost of the studies of noise-induced phenomena assume that the noise source is Gaussian because of the possibility of obtaining some analytical results when working with Gaussian noises. The use of non-Gaussian noises is rare, mainly because of the difficulties in handling them. However, there is experimental evidence indicating that in many phenomena, the noise sources could be non-Gaussian, for example Poisson data and sparsely corrupted data. This thesis provides two classes of algorithms for dealing with some special types of non-Gaussian noise. Obtaining high quality images is very important in many areas of applied sciences, and the first part of this thesis is on expectation maximization (EM)-Type algorithms for image reconstruction with Poisson noise and weighted Gaussian noise. In these two chapters, we proposed general robust expectation maximization (EM)-Type algorithms for image reconstruction when the measured data is corrupted by Poisson noise and weighted Gaussian noise, without and with background emission. This method is separated into two steps: EM step and regularization step. In order to overcome the contrast reduction introduced by some regularizations, we suggested EM-Type algorithms with Bregman iteration by applying a sequence of modified EM-Type algorithms. One algorithm with total variation being the regularization is used for image reconstruction in computed tomography application. The second part of this thesis is on adaptive outlier pursuit method for sparsely corrupted data. In many real world applications, there are all kinds of errors in the measurements during data acquisition and transmission. Some errors will damage the data seriously and make the obtained data containing no information about the true signal, for example, sign flips in measurements for 1-bit compressive sensing and impulse noise in images. Adaptive outlier pursuit is used to detect the outlier and reconstruct the image or signal by iteratively reconstructing the image or signal and adaptively pursuing the outlier. Adaptive outlier pursuit method is used for robust 1-bit compressive sensing and impulse noise removal in chapters 4 and 5 respectively.
Author: Mohammad Rostami
Publisher: Springer
Published: 2013-05-15
Total Pages: 77
ISBN-13: 3319003666
DOWNLOAD EBOOKThis book discusses compressive sensing in the presence of side information. Compressive sensing is an emerging technique for efficiently acquiring and reconstructing a signal. Interesting instances of Compressive Sensing (CS) can occur when, apart from sparsity, side information is available about the source signals. The side information can be about the source structure, distribution, etc. Such cases can be viewed as extensions of the classical CS. In these cases we are interested in incorporating the side information to either improve the quality of the source reconstruction or decrease the number of samples required for accurate reconstruction. In this book we assume availability of side information about the feasible region. The main applications investigated are image deblurring for optical imaging, 3D surface reconstruction, and reconstructing spatiotemporally correlated sources. The author shows that the side information can be used to improve the quality of the reconstruction compared to the classic compressive sensing. The book will be of interest to all researchers working on compressive sensing, inverse problems, and image processing.
Author: Swetha Prasad
Publisher:
Published: 2005
Total Pages: 92
ISBN-13:
DOWNLOAD EBOOK[Author's abstract] The recent increase in the wide use of digital imaging technologies in consumer (e.g., digital video) and other markets (e.g., security and military) has brought with it a simultaneous demand for higher resolution images, or super resolution images, as popularly termed. Most of the super resolution techniques available in literature assume a Gaussian noise model which restricts their applicability and analysis to a particular data set. In order to make the reconstruction framework robust to the impulsive noise, a more generalized model is necessary. This thesis investigates a technique called zoom based robust super resolution technique to reconstruct a super resolved image from a set of low resolution images zoomed to different zoom factors. The proposed reconstruction algorithm based on the M estimator method effectively combats the impulsive noise present in the low resolution images. This robustness of the proposed algorithm is also confirmed by the numerical results.
Author: Lazaros S. Iliadis
Publisher: Springer
Published: 2012-09-22
Total Pages: 520
ISBN-13: 3642334091
DOWNLOAD EBOOKThis book constitutes the refereed proceedings of the 8th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2012, held in Halkidiki, Greece, in September 2012. The 44 revised full papers and 5 revised short papers presented were carefully reviewed and selected from 98 submissions. The papers are organized in topical sections on ANN-classification and pattern recognition, optimization - genetic algorithms, artificial neural networks, learning and mining, fuzzy logic, classification - pattern recognition, multi-agent systems, multi-attribute DSS, clustering, image-video classification and processing, and engineering applications of AI and artificial neural networks.
Author: Mickael Aghajarian
Publisher:
Published: 2021
Total Pages: 83
ISBN-13:
DOWNLOAD EBOOKImage noise is unwanted fluctuations in pixel intensities that is often inevitable during the process of acquisition, compression, and transmission for many reasons such as imperfections in capturing instruments, limitations of analog-to-digital converters, and interference in transmission channels. The existence of noise not only degrades the visual quality of images but also adversely affects the performance of image processing and computer vision tasks, such as classification, detection, and segmentation. Thus, removing or attenuating the effect of image noise (i.e., image denoising) is often an essential preprocessing task in the field of image processing and computer vision. In this dissertation, we addressed three image noises: salt-and-pepper (SAP) impulse noise, random-valued impulse noise (RVIN), and Gaussian noise. In order to restore images contaminated by SAP impulse noise, we used the modified mean filter and total variation of corrupted pixels that was minimized by using convex optimization. For RVIN, we implemented a three-step method that restored images by estimating the noise density, detecting the noisy pixels, and applying a modified weighted mean filter to the detected noisy pixels. For images corrupted by Gaussian noise, we proposed a deep convolutional neural network that handled a wide range of noise levels by using two trained models, one for low noise and the other for high noise levels. We compared the performance of our noise removal methods with other state-of-the-art algorithms and in the vast majority of the cases, our method outperformed other image denoising algorithms which showed the effectiveness of the proposed methods.
Author: Joao Manuel RS Tavares
Publisher: CRC Press
Published: 2013-10-01
Total Pages: 450
ISBN-13: 1315812924
DOWNLOAD EBOOKComputational Vision and Medical Image Processing. VIPIMAGE 2013 contains invited lectures and full papers presented at VIPIMAGE 2013 - IV ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing (Funchal, Madeira Island, Portugal, 14-16 October 2013). International contributions from 16 countries provide a comprehensive cov
Author: Jing Qin
Publisher:
Published: 2013
Total Pages: 186
ISBN-13:
DOWNLOAD EBOOKSignal/image processing and reconstruction based on mathematical modeling and computational techniques have been well developed and still attract much attention due to their broad applications. It becomes challenging to build mathematical models if the given data lacks some certainties. Prior information, including geometric priors, high frequency priors, spatially variant intensity variations and image regularities, assists to establish mathematical models by providing a more accurate description of the underlying signal/image. We have been exploring applications of the extracted prior information in two directions: integrating prior information into the image denoising explained in nonlocal means (NL-means) denoising framework; enhancing the compressive sensing signal/image reconstruction with the guidance of prior information. The first topic is geometric information based image denoising, where we develop a segmentation boosted image denoising scheme, balancing the removal of excessive noise and preservation of fine features. By virtue of segmentation algorithms and more general geometry extraction schemes, we are able to obtain the phase or geometric prior information. Based on the NL-means method, we introduce a mutual position function to ensure that averaging is only taken over pixels in the same image phase. To further improve the performance, we provide the respective selection scheme for the convolution kernel and the weight function. To address the unreliable segmentation due to the presence of excessive noise, the phase prior is relaxed to a more general geometric prior. The second topic is prior information guided compressive sensing signal/image reconstruction. Concerning the 1D signal reconstruction, we extract high frequency subbands as prior to boost the subsequent reconstruction. In 2D image reconstruction realm, we propose a novel two-stage intensity variation prior guided image reconstruction method using pixel-to-pixel varying weights associated to the total variation. By incorporating high order image regularity prior, we develop one total generalized variation (TGV) based image reconstruction model. Unlike the traditional wavelet which is only able to detect locations of singularities, shearlet transform can efficiently provide more geometric information of singularities in images, e.g. direction. Therefore we adopt the shearlet transform to boost the sparsity in image reconstruction algorithms. In addition, our work in signal/image denoising and reconstruction can be easily generalized to deal with other kinds of noise or measurements.
Author: Federico Benvenuto
Publisher:
Published: 2010
Total Pages: 136
ISBN-13:
DOWNLOAD EBOOKIn this thesis, we investigate a set of algorithms for image reconstruction (IR). In chapter 3, we study the existence of the ML solutions in the IR problem corrupted by a mixture of Gaussian and Poisson noise. We give the conditions for existence of the solution of the ML problem. Moreover, we show that the expected value of the IR error of the Landweber algorithm with respect to the noise statistics and to a particular class of eigenvalue distributions (which approximate the real distribution of the eigenvalues of an imaging system) is really semi-convergent with respect to the "true" solution. In chapter 4 we give an approximation of the standard algorithm for Maximum Likelihood IR in the case of a mixture of Gaussian and Poisson noise. In chapter 5, we have applied SGP method for IR in the case of an ill-conditioned problem with data affected by Gaussian noise. We have performed several numerical simulations verifying the efficiency of the SGP method. We have also compared SGP with respect to the classical known algorithms. In chapter 7, we propose a semi-blind deconvolution suitable for the specific case in study, in which the impulse response function depends on one parameter. Simulation results show that this method efficiently estimates the parameter. In chapter 7, we propose a myopic deconvolution for astronomical IR useful when the PSF is measured as well as the date. Hence only a noisy PSF is available. This method, starting from the joint probability between the two random variables, the data and the measured PSF, lead to the minimization of a separately convex functional. A comparison with classical methods is done. The efficiency of myopic method is shown.
Author: James E. Fowler
Publisher: Foundations and Trends(r) in S
Published: 2012
Total Pages: 134
ISBN-13: 9781601985200
DOWNLOAD EBOOKBlock-Based Compressed Sensing of Images and Video overviews the emerging concept of compressed sensing (CS) with a particular focus on recent proposals for its use with a variety of imaging media, including still images, motion video, as well as multiview images and video. Throughout, it considers a variety of CS reconstruction techniques proposed in recent literature and examines relative performance of several prominent reconstruction algorithms for each of the various imagery formats. Particular emphasis is placed on block-based measurement and reconstruction which has the advantages of significantly reduced memory and computation with respect to other approaches relying on full-frame CS measurement operators. Block-Based Compressed Sensing of Images and Video employs extensive experimental comparisons to evaluate various prominent reconstruction algorithms for still-image, motion-video, and multiview scenarios in terms of both reconstruction quality as well as computational complexity. It is not intended to serve as an indepth tutorial on the theory or mathematics of compressed sensing. The coverage of CS theory is brief, while the specifics of the application of block-based compressed sensing (BCS) to natural imagery consume the bulk of the discussion.
