To see the other types of publications on this topic, follow the link: Denoising Image.
Dissertations / Theses on the topic 'Denoising Image'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Denoising Image.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Zhang, Jiachao. "Image denoising for real image sensors." University of Dayton / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1437954286.
Full text
2
Ghazel, Mohsen. "Adaptive Fractal and Wavelet Image Denoising." Thesis, University of Waterloo, 2004. http://hdl.handle.net/10012/882.
Full textAbstract:
The need for image enhancement and restoration is encountered in many practical applications. For instance, distortion due to additive white Gaussian noise (AWGN) can be caused by poor quality image acquisition, images observed in a noisy environment or noise inherent in communication channels. In this thesis, image denoising is investigated. After reviewing standard image denoising methods as applied in the spatial, frequency and wavelet domains of the noisy image, the thesis embarks on the endeavor of developing and experimenting with new image denoising methods based on fractal and wavelet transforms. In particular, three new image denoising methods are proposed: context-based wavelet thresholding, predictive fractal image denoising and fractal-wavelet image denoising. The proposed context-based thresholding strategy adopts localized hard and soft thresholding operators which take in consideration the content of an immediate neighborhood of a wavelet coefficient before thresholding it. The two fractal-based predictive schemes are based on a simple yet effective algorithm for estimating the fractal code of the original noise-free image from the noisy one. From this predicted code, one can then reconstruct a fractally denoised estimate of the original image. This fractal-based denoising algorithm can be applied in the pixel and the wavelet domains of the noisy image using standard fractal and fractal-wavelet schemes, respectively. Furthermore, the cycle spinning idea was implemented in order to enhance the quality of the fractally denoised estimates. Experimental results show that the proposed image denoising methods are competitive, or sometimes even compare favorably with the existing image denoising techniques reviewed in the thesis. This work broadens the application scope of fractal transforms, which have been used mainly for image coding and compression purposes.
3
Li, Zhi. "Variational image segmentation, inpainting and denoising." HKBU Institutional Repository, 2016. https://repository.hkbu.edu.hk/etd_oa/292.
Full textAbstract:
Variational methods have attracted much attention in the past decade. With rigorous mathematical analysis and computational methods, variational minimization models can handle many practical problems arising in image processing, such as image segmentation and image restoration. We propose a two-stage image segmentation approach for color images, in the first stage, the primal-dual algorithm is applied to efficiently solve the proposed minimization problem for a smoothed image solution without irrelevant and trivial information, then in the second stage, we adopt the hillclimbing procedure to segment the smoothed image. For multiplicative noise removal, we employ a difference of convex algorithm to solve the non-convex AA model. And we also improve the non-local total variation model. More precisely, we add an extra term to impose regularity to the graph formed by the weights between pixels. Thin structures can benefit from this regularization term, because it allows to adapt the weights value from the global point of view, thus thin features will not be overlooked like in the conventional non-local models. Since now the non-local total variation term has two variables, the image u and weights v, and it is concave with respect to v, the proximal alternating linearized minimization algorithm is naturally applied with variable metrics to solve the non-convex model efficiently. In the meantime, the efficiency of the proposed approaches is demonstrated on problems including image segmentation, image inpainting and image denoising.
4
Danda, Swetha. "Generalized diffusion model for image denoising." Morgantown, W. Va. : [West Virginia University Libraries], 2007. https://eidr.wvu.edu/etd/documentdata.eTD?documentid=5481.
Full textAbstract:
Thesis (M.S.)--West Virginia University, 2007.Title from document title page. Document formatted into pages; contains viii, 62 p. : ill. Includes abstract. Includes bibliographical references (p. 59-62).
5
Deng, Hao. "Mathematical approaches to digital color image denoising." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/31708.
Full textAbstract:
Thesis (Ph.D)--Mathematics, Georgia Institute of Technology, 2010.Committee Chair: Haomin Zhou; Committee Member: Luca Dieci; Committee Member: Ronghua Pan; Committee Member: Sung Ha Kang; Committee Member: Yang Wang. Part of the SMARTech Electronic Thesis and Dissertation Collection.
6
Hussain, Israr. "Non-gaussianity based image deblurring and denoising." Thesis, University of Manchester, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.489022.
Full text
7
Sarjanoja, S. (Sampsa). "BM3D image denoising using heterogeneous computing platforms." Master's thesis, University of Oulu, 2015. http://urn.fi/URN:NBN:fi:oulu-201504141380.
Full textAbstract:
Noise reduction is one of the most fundamental digital image processing problems, and is often designed to be solved at an early stage of the image processing path. Noise appears on the images in many different ways, and it is inevitable. In general, various image processing algorithms perform better if their input is as error-free as possible. In order to keep the processing delays small in different computing platforms, it is important that the noise reduction is performed swiftly. The recent progress in the entertainment industry has led to major improvements in the computing capabilities of graphics cards. Today, graphics circuits consist of several hundreds or even thousands of computing units. Using these computing units for general-purpose computation is possible with OpenCL and CUDA programming interfaces. In applications where the processed data is relatively independent, using parallel computing units may increase the performance significantly. Graphics chips enabled with general-purpose computation capabilities are becoming more common also in mobile devices. In addition, photography has never been as popular as it is nowadays by using mobile devices. This thesis aims to implement the calculation of the state-of-the-art technology used in noise reduction, block-matching and three-dimensional filtering (BM3D), to be executed in heterogeneous computing environments. This study evaluates the performance of the presented implementations by making comparisons with existing implementations. The presented implementations achieve significant benefits from the use of parallel computing devices. At the same time the comparisons illustrate general problems in the utilization of using massively parallel processing for the calculation of complex imaging algorithmsKohinanpoisto on yksi keskeisimmistä digitaaliseen kuvankäsittelyyn liittyvistä ongelmista, joka useimmiten pyritään ratkaisemaan jo signaalinkäsittelyvuon varhaisessa vaiheessa. Kohinaa ilmestyy kuviin monella eri tavalla ja sen esiintyminen on väistämätöntä. Useat kuvankäsittelyalgoritmit toimivat paremmin, jos niiden syöte on valmiiksi mahdollisimman virheetöntä käsiteltäväksi. Jotta kuvankäsittelyviiveet pysyisivät pieninä eri laskenta-alustoilla, on tärkeää että myös kohinanpoisto suoritetaan nopeasti. Viihdeteollisuuden kehityksen myötä näytönohjaimien laskentateho on moninkertaistunut. Nykyisin näytönohjainpiirit koostuvat useista sadoista tai jopa tuhansista laskentayksiköistä. Näiden laskentayksiköiden käyttäminen yleiskäyttöiseen laskentaan on mahdollista OpenCL- ja CUDA-ohjelmointirajapinnoilla. Rinnakkaislaskenta usealla laskentayksiköllä mahdollistaa suuria suorituskyvyn parannuksia käyttökohteissa, joissa käsiteltävä tieto on toisistaan riippumatonta tai löyhästi riippuvaista. Näytönohjainpiirien käyttö yleisessä laskennassa on yleistymässä myös mobiililaitteissa. Lisäksi valokuvaaminen on nykypäivänä suosituinta juuri mobiililaitteilla. Tämä diplomityö pyrkii selvittämään viimeisimmän kohinanpoistoon käytettävän tekniikan, lohkonsovitus ja kolmiulotteinen suodatus (block-matching and three-dimensional filtering, BM3D), laskennan toteuttamista heterogeenisissä laskentaympäristöissä. Työssä arvioidaan esiteltyjen toteutusten suorituskykyä tekemällä vertailuja jo olemassa oleviin toteutuksiin. Esitellyt toteutukset saavuttavat merkittäviä hyötyjä rinnakkaislaskennan käyttämisestä. Samalla vertailuissa havainnollistetaan yleisiä ongelmakohtia näytönohjainlaskennan hyödyntämisessä monimutkaisten kuvankäsittelyalgoritmien laskentaan
8
Houdard, Antoine. "Some advances in patch-based image denoising." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLT005/document.
Full textAbstract:
Cette thèse s'inscrit dans le contexte des méthodes non locales pour le traitement d'images et a pour application principale le débruitage, bien que les méthodes étudiées soient suffisamment génériques pour être applicables à d'autres problèmes inverses en imagerie. Les images naturelles sont constituées de structures redondantes, et cette redondance peut être exploitée à des fins de restauration. Une manière classique d’exploiter cette auto-similarité est de découper l'image en patchs. Ces derniers peuvent ensuite être regroupés, comparés et filtrés ensemble.Dans le premier chapitre, le principe du "global denoising" est reformulé avec le formalisme classique de l'estimation diagonale et son comportement asymptotique est étudié dans le cas oracle. Des conditions précises à la fois sur l'image et sur le filtre global sont introduites pour assurer et quantifier la convergence.Le deuxième chapitre est consacré à l'étude d’a priori gaussiens ou de type mélange de gaussiennes pour le débruitage d'images par patches. Ces a priori sont largement utilisés pour la restauration d'image. Nous proposons ici quelques indices pour répondre aux questions suivantes : Pourquoi ces a priori sont-ils si largement utilisés ? Quelles informations encodent-ils ?Le troisième chapitre propose un modèle probabiliste de mélange pour les patchs bruités, adapté à la grande dimension. Il en résulte un algorithme de débruitage qui atteint les performance de l'état-de-l'art.Le dernier chapitre explore des pistes d'agrégation différentes et propose une écriture de l’étape d'agrégation sous la forme d'un problème de moindre carrésThis thesis studies non-local methods for image processing, and their application to various tasks such as denoising. Natural images contain redundant structures, and this property can be used for restoration purposes. A common way to consider this self-similarity is to separate the image into "patches". These patches can then be grouped, compared and filtered together.In the first chapter, "global denoising" is reframed in the classical formalism of diagonal estimation and its asymptotic behaviour is studied in the oracle case. Precise conditions on both the image and the global filter are introduced to ensure and quantify convergence.The second chapter is dedicated to the study of Gaussian priors for patch-based image denoising. Such priors are widely used for image restoration. We propose some ideas to answer the following questions: Why are Gaussian priors so widely used? What information do they encode about the image?The third chapter proposes a probabilistic high-dimensional mixture model on the noisy patches. This model adopts a sparse modeling which assumes that the data lie on group-specific subspaces of low dimensionalities. This yields a denoising algorithm that demonstrates state-of-the-art performance.The last chapter explores different way of aggregating the patches together. A framework that expresses the patch aggregation in the form of a least squares problem is proposed
9
Karam, Christina Maria. "Acceleration of Non-Linear Image Filters, and Multi-Frame Image Denoising." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1575976497271633.
Full text
10
Tuncer, Guney. "A Java Toolbox For Wavelet Based Image Denoising." Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/12608037/index.pdf.
Full textAbstract:
Wavelet methods for image denoising have became widespread for the last decade. The effectiveness of this denoising scheme is influenced by many factors. Highlights can be listed as choosing of wavelet used, the threshold
determination and transform level selection for thresholding. For threshold calculation one of the classical solutions is Wiener filter as a linear estimator. Another one is VisuShrink using global thresholding for nonlinear area. The purpose of this work is to develop a Java toolbox which is used to find best denoising schemes for distinct image types particularly Synthetic Aperture Radar (SAR) images. This can be accomplished by comparing these basic methods with well known data adaptive thresholding methods such as SureShrink, BayeShrink, Generalized Cross Validation and Hypothesis Testing. Some nonwavelet denoising process are also introduced. Along with simple mean and median filters, more statistically adaptive median, Lee, Kuan and Frost filtering techniques are also tested to assist wavelet based denoising scheme. All of these methods on the basis of wavelet models and some traditional methods will be
implemented in pure java code using plug-in concept of ImageJ which is a popular image processing tool written in Java.
11
Michael, Simon. "A Comparison of Data Transformations in Image Denoising." Thesis, Uppsala universitet, Statistiska institutionen, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-375715.
Full textAbstract:
The study of signal processing has wide applications, such as in hi-fi audio, television, voice recognition and many other areas. Signals are rarely observed without noise, which obstruct our analysis of signals. Hence, it is of great interest to study the detection, approximation and removal of noise. In this thesis we compare two methods for image denoising. The methods are each based on a data transformation. Specifically, Fourier Transform and Singular Value Decomposition are utilized in respective methods and compared on grayscale images. The comparison is based on the visual quality of the resulting image, the maximum peak signal-to-noise ratios attainable for the respective methods and their computational time. We find that the methods are fairly equal in visual quality. However, the method based on the Fourier transform scores higher in peak signal-to-noise ratio and demands considerably less computational time.
12
Aparnnaa. "Image Denoising and Noise Estimation by Wavelet Transformation." Kent State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=kent1555929391906805.
Full text
13
Lind, Johan. "Evaluating CNN-based models for unsupervised image denoising." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176092.
Full textAbstract:
Images are often corrupted by noise which reduces their visual quality and interferes with analysis. Convolutional Neural Networks (CNNs) have become a popular method for denoising images, but their training typically relies on access to thousands of pairs of noisy and clean versions of the same underlying picture. Unsupervised methods lack this requirement and can instead be trained purely using noisy images. This thesis evaluated two different unsupervised denoising algorithms: Noise2Self (N2S) and Parametric Probabilistic Noise2Void (PPN2V), both of which train an internal CNN to denoise images. Four different CNNs were tested in order to investigate how the performance of these algorithms would be affected by different network architectures. The testing used two different datasets: one containing clean images corrupted by synthetic noise, and one containing images damaged by real noise originating from the camera used to capture them. Two of the networks, UNet and a CBAM-augmented UNet resulted in high performance competitive with the strong classical denoisers BM3D and NLM. The other two networks - GRDN and MultiResUNet - on the other hand generally caused poor performance.
14
Liu, Xiaoyang. "Advanced numerical methods for image denoising and segmentation." Thesis, University of Greenwich, 2013. http://gala.gre.ac.uk/11954/.
Full textAbstract:
Image denoising is one of the most major steps in current image processing. It is a pre-processing step which aims to remove certain unknown, random noise from an image and obtain an image free of noise for further image processing, such as image segmentation. Image segmentation, as another branch of image processing, plays a significant role in connecting low-level image processing and high-level image processing. Its goal is to segment an image into different parts and extract meaningful information for image analysis and understanding. In recent years, methods based on PDEs and variational functional became very popular in both image denoising and image segmentation. These two branches of methods are presented and investigated in this thesis. In this thesis, several typical methods based on PDE are reviewed and examined. These include the isotropic diffusion model, the anisotropic diffusion model (the P-M model), the fourth-order PDE model (the Y-K model), and the active contour model in image segmentation. Based on the analysis of behaviours of each model, some improvements are proposed. First, a new coefficient is provided for the P-M model to obtain a well-posed model and reduce the “block effect”. Second, a weighted sum operator is used to replace the Laplacian operator in the Y-K model. Such replacement can relieve the creation of the speckles which is brought in by the Y-K model and preserve more details. Third, an adaptive relaxation method with a discontinuity treatment is proposed to improve the numerical solution of the Y-K model. Fourth, an active contour model coupling with the anisotropic diffusion model is proposed to build a noise-resistance segmentation method. Finally, in this thesis, three ways of deriving PDE are developed and summarised. The issue of PSNR is also discussed at the end of the thesis.
15
Liao, Zhiwu. "Image denoising using wavelet domain hidden Markov models." HKBU Institutional Repository, 2005. http://repository.hkbu.edu.hk/etd_ra/616.
Full text
16
De, Santis Simone. "Quantum Median Filter for Total Variation denoising." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Find full textAbstract:
In this work we present Quantum Median Filter, an image processing algorithm for applying Total Variation denoising to quantum image representations.
After a brief introduction to TV model and quantum computing, we present QMF algorithm and discuss its design and efficiency; then we implement and simulate the quantum circuit using Qiskit library; finally we apply it to a set of noisy images, in order to compare and evaluate experimental results.
17
Zhang, Chen. "Blind Full Reference Quality Assessment of Poisson Image Denoising." University of Dayton / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1398875743.
Full text
18
McGraw, Tim E. "Denoising, segmentation and visualization of diffusion weighted MRI." [Gainesville, Fla.] : University of Florida, 2005. http://purl.fcla.edu/fcla/etd/UFE0011618.
Full text
19
Maitree, Rapeepan, Gloria J. Guzman Perez-Carrillo, Joshua S. Shimony, H. Michael Gach, Anupama Chundury, Michael Roach, H. Harold Li, and Deshan Yang. "Adaptive anatomical preservation optimal denoising for radiation therapy daily MRI." SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS, 2017. http://hdl.handle.net/10150/626083.
Full textAbstract:
Low-field magnetic resonance imaging (MRI) has recently been integrated with radiation therapy systems to provide image guidance for daily cancer radiation treatments. The main benefit of the low-field strength is minimal electron return effects. The main disadvantage of low-field strength is increased image noise compared to diagnostic MRIs conducted at 1.5 T or higher. The increased image noise affects both the discernibility of soft tissues and the accuracy of further image processing tasks for both clinical and research applications, such as tumor tracking, feature analysis, image segmentation, and image registration. An innovative method, adaptive anatomical preservation optimal denoising (AAPOD), was developed for optimal image denoising, i. e., to maximally reduce noise while preserving the tissue boundaries. AAPOD employs a series of adaptive nonlocal mean (ANLM) denoising trials with increasing denoising filter strength (i. e., the block similarity filtering parameter in the ANLM algorithm), and then detects the tissue boundary losses on the differences of sequentially denoised images using a zero-crossing edge detection method. The optimal denoising filter strength per voxel is determined by identifying the denoising filter strength value at which boundary losses start to appear around the voxel. The final denoising result is generated by applying the ANLM denoising method with the optimal per-voxel denoising filter strengths. The experimental results demonstrated that AAPOD was capable of reducing noise adaptively and optimally while avoiding tissue boundary losses. AAPOD is useful for improving the quality of MRIs with low-contrast-to-noise ratios and could be applied to other medical imaging modalities, e.g., computed tomography. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
20
Miller, Sarah Victoria. "Mulit-Resolution Aitchison Geometry Image Denoising for Low-Light Photography." University of Dayton / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1596444315236623.
Full text
21
Lee, Kai-wah. "Mesh denoising and feature extraction from point cloud data." Click to view the E-thesis via HKUTO, 2009. http://sunzi.lib.hku.hk/hkuto/record/B42664330.
Full text
22
Lee, Kai-wah, and 李啟華. "Mesh denoising and feature extraction from point cloud data." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2009. http://hub.hku.hk/bib/B42664330.
Full text
23
Quan, Jin. "Image Denoising of Gaussian and Poisson Noise Based on Wavelet Thresholding." University of Cincinnati / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1380556846.
Full text
24
Jin, Xiaodan. "Poisson Approximation to Image Sensor Noise." University of Dayton / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1292306911.
Full text
25
Kim, Il-Ryeol. "Wavelet domain partition-based signal processing with applications to image denoising and compression." Access to citation, abstract and download form provided by ProQuest Information and Learning Company; downloadable PDF file 2.98 Mb., 119 p, 2006. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:3221054.
Full text
26
Zhang, Chen. "Poisson Noise Parameter Estimation and Color Image Denoising for Real Camera Hardware." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1575968356242716.
Full text
27
Kim, Yunho. "Variational methods theory and its applications to image deblurring and denoising problems /." Diss., Restricted to subscribing institutions, 2009. http://proquest.umi.com/pqdweb?did=1872146111&sid=1&Fmt=2&clientId=1564&RQT=309&VName=PQD.
Full text
28
Cheng, Wei. "Studies on NDT Image Denoising by Wavelet Transform and Self-Orgnizing Maps." 京都大学 (Kyoto University), 2004. http://hdl.handle.net/2433/147636.
Full text
29
Balster, Eric J. "Video compression and rate control methods based on the wavelet transform." Columbus, Ohio : Ohio State University, 2004. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1086098540.
Full textAbstract:
Thesis (Ph. D.)--Ohio State University, 2003.Title from first page of PDF file. Document formatted into pages; contains xxv, 142 p.; also includes graphics. Includes abstract and vita. Advisor: Yuan F. Zheng, Dept. of Electrical and Computer Engineering. Includes bibliographical references (p. 135-142).
30
Wang, Tianyang. "A Novel Image Retrieval Strategy Based on VPD and Depth with Pre-Processing." OpenSIUC, 2015. https://opensiuc.lib.siu.edu/dissertations/1054.
Full textAbstract:
This dissertation proposes a comprehensive working flow for image retrieval. It contains four components: denoising, restoration, color features extraction, and depth feature extraction. We propose a visual perceptual descriptor (VPD) to extract color features from an image. Gradient direction is calculated at each pixel, and the VPD is moved over the entire image to locate regions with similar gradient direction. Color features are extracted only at these pixels. Experiments demonstrate that VPD is an effective and reliable descriptor in image retrieval. We propose a novel depth feature for image retrieval. Regarding any 2D image as the convolution of a corresponding sharp image and a Gaussian kernel with unknown blur amount. Sparse depth map is computed as the absolute difference of the original image and its sharp version. Depth feature is extracted as the nuclear norm of the sparse depth map. Experiments validate the effectiveness of this approach on depth recovery and image retrieval. We present a model for image denoising. A gradient item is incorporated, and can be merged into the original model based on geometric measure theory. Experiments illustrate this model is effective for image denoising, and it can improve the retrieval performance by denoising a query image. A model is proposed for image restoration. It is an extension of the traditional singular value thresholding (SVT) algorithm, addressing the issue that SVT cannot recover a matrix with missing rows or columns. Proposed is a way to fill such rows and columns, and then apply SVT to restore the damaged image. The pre-filled entries are recomputed by averaging its neighboring pixels. Experiments demonstrate the effectiveness of this model on image restoration, and it can improve the retrieval performance by restoring a damaged query image. Finally, the capability of this working flow is tested. Experiments demonstrate its effectiveness in image retrieval.
31
Qin, Jing. "Prior Information Guided Image Processing and Compressive Sensing." Case Western Reserve University School of Graduate Studies / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=case1365020074.
Full text
32
George, Ben. "Statistical and Evolutionary Models for the Construction of Facial Composites and Image Denoising." Thesis, University of Kent, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.523637.
Full text
33
Liu, Yang. "Image Denoising: Invertible and General Denoising Frameworks." Phd thesis, 2022. http://hdl.handle.net/1885/270008.
Full textAbstract:
The widespread use of digital cameras has resulted in a massive number of images being taken every day. However, due to the limitations of sensors and environments such as light conditions, the images are usually contaminated by noise. Obtaining visually clean images are essential for the accuracy of downstream high-level vision tasks. Thus, denoising is a crucial preprocessing step.
A fundamental challenge in image denoising is to restore recognizable frequencies in edge and fine-scaled texture regions. Traditional methods usually employ hand-crafted priors to enhance the restoration of these high frequency regions, which seem to be omitted in current deep learning models. We explored whether the clean gradients can be utilized in deep networks as a prior as well as how to incorporate this prior in the networks to boost recovery of missing or obscured picture elements. We present results showing that fusing the pre-denoised images' gradient in the shallow layer contributes to recovering better edges and textures. We also propose a regularization loss term to ensure that the reconstructed images' gradients are close to the clean gradients. Both techniques are indispensable for enhancing the restored image frequencies.
We also studied how to make the network preserve input information for better restoration of the high-frequency details. According to the definition of mutual information, we presented that invertibility is indispensable for information losslessness. Then, we proposed the Invertible Restoring Autoencoder (IRAE) network, a multiscale invertible encoder-decoder network. The superiority of this network was verified on three different low-level tasks, image denoising, JPEG image decompression and image inpainting. IRAE showed a good direction to explore more invertible architectures for image restoration.
We attempted to further reduce the model size of invertible restoration networks. Our intuition was to use the same learned parameters to encode the noisy images in the forward pass and reconstruct the clean images in the backward pass. However, existing invertible networks use the same distribution for both the input and output obtained in the reversed pass. For our noise removal purpose, the input is noisy, but the reversed output is clean, following two different distributions. It was challenging to design lightweight invertible architectures for denoising. We presented InvDN, converting the noisy input to a clean low-resolution image and a noisy latent representation. To address the challenge mentioned above, we replaced the noisy representation with a clean one random sampled from Gaussian during the reverse pass. InvDN achieved state-of-the-art on real image denoising with much fewer parameters and less run time than existing state-of-the-art models. In addition, InvDN could also generate new noisy images for data augmentation.
We also rethought image denoising from a novel aspect and introduced a more general denoising framework. Our framework utilized invertible networks to learn a noisy image distribution, which could be considered as the joint distribution of clean content and noise. The noisy input was mapped to representations in the latent space. A novel disentanglement strategy was applied to the latent representations to obtain the representations for the clean content, which were passed to the reversed network to get the clean image. Since this concept was a novel attempt, we also explored different data augmentation and training strategies for this framework. The proposed FDN was trained and tested from simple to complex tasks on distribution-clear class-specific synthetic noisy datasets, more general remote sensing datasets, and real noisy datasets and achieved competitive results with fewer parameters and faster speed. This work contributed a novel perspective and potential direction to design low-level task models in the future.
34
Hua, Gang. "Noncoherent image denoising." Thesis, 2005. http://hdl.handle.net/1911/17859.
Full textAbstract:
The techniques of Translation Invariant (TI) denoising and statistical modeling are widely used in image denoising. This thesis studies how these techniques exploit location information in images and identifies a class of noncoherent image denoising algorithms. We analyze the performance of TI denoising from the perspective of cyclic-basis reconstruction. It shows that TI denoising achieves an average performance without direct estimation of location information. Motivated by this perspective, we propose a Redundant Quaternion Wavelet Transform (RQWT) which both avoids aliasing and separates local signal energy and location information into quaternion magnitude and phases respectively. RQWT is a natural framework for studying the statistical models in noncoherent image denoisers, because they all ignore quaternion phases. Straightforward signal estimation in the RQWT framework closely matches the state-of-the-art noncoherent image denoisers and provides a natural bound on their performance, thereby showing the importance of exploring location information in quaternion phases.
35
Bao, Yufang. "Nonlinear image denoising methodologies." 2002. http://www.lib.ncsu.edu/theses/available/etd-05172002-131134/unrestricted/etd.pdf.
Full text
36
Cho, Dongwook. "Image denoising using wavelet transforms." Thesis, 2004. http://spectrum.library.concordia.ca/8141/1/MQ94737.pdf.
Full textAbstract:
Image denoising is a fundamental process in image processing, pattern recognition, and computer vision fields. The main goal of image denoising is to enhance or restore a noisy image and help the other system (or human) to understand it better. In this thesis, we discuss some efficient approaches for image denoising using wavelet transforms. Since Donoho proposed a simple thresholding method, many different approaches have been suggested for a decade. They have shown that denoising using wavelet transforms produces superb results. This is because wavelet transform has the compaction property of having only a small number of large coefficients and a large number of small coefficients. In the first part of the thesis, some important wavelet transforms for image denoising and a literature review on the existing methods are described. In the latter part, we propose two different approaches for image denoising. The first approach is to take advantage of the higher order statistical coupling between neighbouring wavelet coefficients and their corresponding coefficients in the parent level with effective translation-invariant wavelet transforms. The other is based on multivariate statistical modeling and the clean coefficients are estimated in a general rule using Bayesian approach. Various estimation expressions can be obtained by a priori probability distribution, called multivariate generalized Gaussian distribution (MGGD). The method can take into account various related information. The experimental results show that both of our methods give comparatively higher PSNR and less visual artifact than other methods.
37
Parida, Satyabrata. "Denoising Of Satellite Images." Thesis, 2014. http://ethesis.nitrkl.ac.in/6612/1/Satyabrata_Parida_PROJECT_THESIS.pdf.
Full textAbstract:
We use images in our day to day life for keeping a record of information or merely to convey a message. There are a number of parameters which determine the quality of an image or a photograph most of which cannot be solved manually without the help of a computer whatsoever
any image that has been captured represents a deteriorated version of the original image. However
its clear that by any means we can never get the ideal image which is hypothetical as it is 100% accurate which is not possible. Our aim in image processing is to get the best possible image with minimum number of errors. In order to come to the conclusion of a certain task the correction of this deteriorated version is of optimal importance. Rectifying too much lighting effects, instance noising, geometrical faults, unwanted colour variations and blur are some of the important
parameters we need to attend to in order to get a good and useful image. In this paper, the deterioration of images because of noising has been addressed. Noise is any undesired information which adversely affects the quality and content of our image. Primary factors responsible for creating noise in an image are the medium through which photograph is taken (climatic and
atmospheric factors like pressure and temperature), the accuracy of the instrument used to take the photograph (for instance camera) and the quantization of data used to store the image.
This noise can be removed by an image processing technique called Image restoration. Image restoration process is concerned with the reconstruction of the original image from a noisy one.That is it tries to perform an operation on the image as the inverse of the imperfections in the image formation system. Degraded image can be perfected by various processes which are actually the reverse of noising. These filtering techniques are very simple and can be applied very easily through software. Some filtering processes have better performance than the others. This depends on the type of noise the image has. These filters are used in a variety of applications efficiently in preprocessing module. In this paper, the restoration performance of Arithmetic mean filter, Geometric mean filter and Median filter have been analyzed. The performance of these filters is analyzed by applying it on satellite images which are affected by Impulse noise, Speckle noise and Gaussian
noise. Since the satellite images are being corrupted by various noises, the satellite images are considered in this paper to analyze the performance of arithmetic mean filter, geometric mean filter and median filter.
By observing the obtained results and PSNR value for various satellite images under different
noises, we have recorded the following conclusion.
• the median filter gives better performance for satellite images affected by impulse noise than
arithmetic mean filter and geometric mean filter.
•the arithmetic mean filter gives better performance for gaussian noise than median filter and
geometric mean filters for all satellite images.
•the arithmetic mean filter gives better performance for speckle noise than median filter and
geometric mean filter for all satellite images.
Median Filter is an image filter that is more effective in situations where white spots and black
spots appear on the image. For this technique the middle value of the m×n window is considered to
replace the black and white pixels.After white spots and black spots appear on the image, it
becomes pretty difficult to find which pixel is the affected pixel. Replacing those affected pixels
with AMF, GMF and HMF is not enough because those pixels are replaced by a value which is not
appropriate to the original one. It is observed that the median filter gives better performance than
AMF and GMF for distorted images. The performance of restoration filter can be increased further
to completely remove noise and to preserve the edges of the image by using both linear and
nonlinear filter together.
38
Mu-Yen, Chen, and 陳木炎. "Radar Image Denoising with Wavelet Packets." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/02378868527279744430.
Full textAbstract:
碩士國立海洋大學
航海技術學系
83
In this thesis, the frame of radar PPI image is treated as a whole for denoising via wavelet packets. To obtain a clean scan for radar observation, the object boundary in PPI image is considered more important than its texture content. Therefore, the complexity of denoising is reduced. Iterated noise estimation (INE) and recursively coefficients thresholding and reconstructing (RCTR) are two major steps is our denoising approach. It is shown that RCTR has better performance than the traditional inverse wavelet transform when the same coefficients thresholding is applied. Moreover, the performance is insensitive to the estimation error of noise variance by INE.
39
LIN, SIN-HONG, and 林信宏. "A wavelet-based image denoising method." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/9qf5dk.
Full textAbstract:
碩士國立臺北科技大學
自動化科技研究所
107
The efficient representation of edges is key to improving the image denoising performance. This motivates us to capture the edges and calculate them with a wavelet transform. A novel image denoising method is proposed by exploiting the image edges information and the multidirectional shrinkage. The image edges preservation effect is achieved by applying the main direction in the wavelet transform. Since the image is perform wavelet transform in different directions, for each pixel we obtain many different estimates, one of which is optimal. A noisy image is decomposed into subbands of LL, LH, HL, and HH in wavelet domain. LL subband contains the low frequency coefficients along with less noise, which can be easily eliminated using TV-based method. More edges and other detailed information like textures are contained in the other three subbands, and we propose a shrinkage method based on the local variance to extract them from high frequency noise. And apply adaptive threshold shrinkage to denoising. The final denoised output is obtained by a weighted averaging of all individual estimates. Experimental results show that our method, compared with other wavelet-based denoising algorithms, can effectively remove noise and preserve detail information such as edges and textures.
40
Lee, Ssu-Rui, and 李思叡. "Image Denoising by Convolutional Neural Network." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/he56yv.
Full textAbstract:
碩士國立清華大學
資訊系統與應用研究所
107
Removing noise from the images to improve image quality is the main challenge in image processing. Especially as the ubiquitous spread of computers, smartphones, the Internet, and social networks, image denoising becomes more and more important. In this work, we extend upon the results of Ulyanov et al.~\cite{Ulyanov_2018_CVPR} and introduce a competitive image denoising method based on the structure characteristic of convolutional neural networks (CNNs). Different from most CNN-based methods which need a large-scale dataset for training, our method only looks at one degraded image and removes noise on itself. This method is not only an application of image denoising but also a point of view for visualizing the property and effect of each element in convolutional neural networks.
41
Singh, Himanshu. "A Survey of Image Denoising Algorithms." Thesis, 2013. http://ethesis.nitrkl.ac.in/5454/1/109cs0191thesis.pdf.
Full textAbstract:
Images play an important role in conveying important information but the images received after
transmission are often corrupted and deviate from the original value.
When an Image is formed various factors such as lighting spectra, source, intensity and camera
Characteristics (sensor response, lenses) affect the image. The major factor that reduces the
quality of the image is Noise. It hides the important details of images and changes value of image
pixels at key locations causing blurring and various other deformities. We have to remove noises
from the images without loss of any image information. Noise removal is the preprocessing stage
of image processing. There are many types of noises which corrupt the images. These noises are
appeared on images in different ways: at the time of acquisition due to noisy sensors, due to
faulty scanner or due to faulty digital camera, due to transmission channel errors, due to
corrupted storage media.
The image needs image denoising before it can be used in applications to obtain accurate results.
Various types of noises that create fault in image are discussed. Many image denoising
algorithms exist none of them are universal and their performance largely depends upon the type
of image and the type of noise. In this paper we will be discussing some of the image denoising
algorithms and comparing them with each other. A quantitative measure of the image denoising
algorithms is provided by the signal to noise ratio and the computation time of various
algorithms working on a provided noisy image.
42
Bhattacharya, Ranita. "Study of Color Image Denoising Filters." Thesis, 2016. http://ethesis.nitrkl.ac.in/9113/1/2016_MT_RBhattacharya.pdf.
Full textAbstract:
Image Denoising is an essential pre-processing task before the image is further processed by segmentation, feature extraction, texture analysis etc. Denoising is employed to evacuate the noise while retaining the sharp edges and other texture details of the image however much as could reasonably be expected. This noise gets present amid acquisition, transmission, and storage processes. Visual quality of the image is degraded due to the noise introduced in it. The noise considered in this thesis is additive white Gaussian noise (AWGN). Some spatial-Domain filters like Mean filter, Median filter, Weighted median filter, Wiener filter etc. have been studied in this work for suppression of AWGN. The recently developed Block matching and 3D filtering approach have also been performed efficiently under high variance of noise . Performance of these filters are compared in terms of peak-signal-to-noise-ratio (PSNR), structural similarity index (SSIM). Results of ten different standard color images have been compared under varied noise levels. The Mean filter for Gaussian noise removal under low noise conditions works efficiently. Median filter , weighted median filter and Wiener filter performs better than mean filter.
BM3D is a state of the art technique, which gives better performance than all the other techniques studied here. All the studied filters are applied on the color images. As BM3D outperforms all of the techniques studied here, our main focus is BM3D. BM3D is a transform domain filtering method which exploit the high correlation between the similar blocks in a natural image. All similar image blocks are collected in group in this method, and then denoising is done in a 3D transform domain. Denoising is done by hard thresholding and Wiener shrinkage. BM3D is applied for color image denoising after converting the image from RGB color space to YUV color space so that the edge details of the image can be extracted, then the filtering is applied on the noisy image.
43
Santra, Ayan Kanti. "Denoising Images Under Multiplicative Noise." Thesis, 2013. http://ethesis.nitrkl.ac.in/4790/1/211EE1328.pdf.
Full textAbstract:
Generally the speckle noise occurred in images of different modalities due to random variation of pixel values. To denoise these images, it is necessary to apply various filtering techniques. So far there are lots of filtering methods proposed in literature which includes the Wiener filtering and Wavelet based thresholding approach to denoise such type of noisy images. This thesis analyse exiting Wiener filtering for image restoration with variable window size. However this restoration may not exhibit satisfactory performances with respect to standard indices like Structural Similarity Index Measure (SSIM), Signal-to-Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), and Mean Square Error (MSE). Literature indicates that Curvelet transform represents natural image better than any other transformations. Therefore, curvelet coefficient can be used to segment true image and noise. The aim of the thesis to characterize the multiplicative noise in Curvelet transform domain. Subsequently a threshold based denoising algorithm has been developed using hard and MCET thresholding techniques. Finally, the denoised image was compared with original image using some quantifying statistical indices such as SSIM, MSE, SNR and PSNR for different noise variance which The experimental results demonstrate its efficacy over Wiener filtering method.
44
Zhang, Wen. "General Adaptive Monte Carlo Bayesian Image Denoising." Thesis, 2010. http://hdl.handle.net/10012/4920.
Full textAbstract:
Image noise reduction, or denoising, is an active area of research, although many of the techniques cited in the literature mainly target additive white noise. With an emphasis on signal-dependent noise, this thesis presents the General Adaptive Monte Carlo Bayesian Image Denoising (GAMBID) algorithm, a model-free approach based on random sampling. Testing is conducted on synthetic images with two different signal-dependent noise types as well as on real synthetic aperture radar and ultrasound images. Results show that GAMBID can achieve state-of-the-art performance, but suffers from some limitations in dealing with textures and fine low-contrast features. These aspects can by addressed in future iterations when GAMBID is expanded to become a versatile denoising framework.
45
Lee, Yu-lun, and 李育倫. "Diffusion Weighted Image Denoising by Wavelet Transform." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/45251434655663101996.
Full textAbstract:
碩士國立雲林科技大學
工業工程與管理研究所碩士班
99
Diffusion tensor imaging (DTI) is one of very common medical imaging, which composed by a series Diffusion weighted imaging. It is a non-invasive technique and it can provide the direction of nerve fiber in our brain. However, some noises, which generated by DTI rapid imaging, patients state and other factors, reduce the image quality of DWI. Noises make tractography produce incorrect result. In this study, we add noises in the simulation images, and use wavelet transform and anisotropic filter to denoising. We compare the performance of two filters, and choice a better filter used in practical images. The result of simulation data show that, wavelet transform significantly lower than anisotropic filter in average error. After denoising, the amplitude of measure index FA value average error shrink from 0.00832 to 0.001964, and MD value average error form 0.008096 to 0.002108, the average of measure index can be close to simulation image. There have four patients with metastatic tumor and four normal subjects in practical data. The regions of interest (ROI) include region of tumor, region of edema, region of edema symmetrical and region of white matter in normal subjects. We compute the measure index FA and MD, draw scatter plots, and then we compare the results. It show that, in different areas test, FA and MD value significantly different after denoising, in different subjects test, FA value significantly different after denoising, and MD value do not significantly different after denoising. The average deviation of FA value is 0.079775 and MD value is 0.038185. The result can be one of reference for medical imaging quantitative basis.
46
Chu, Chia-Min, and 朱家敏. "Adaptive Anisotropic Diffusion Equation for Image Denoising." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/98930738395777679872.
Full textAbstract:
碩士國立中興大學
應用數學系所
96
In this thesis, we present an adaptive correlation method for the image denoising and edge preservation. Several nonlinear diffusion filters have been widely implemented; however, it is still very difficult to preserve the image edge and clean the noise simultaneously. We propose a new anisotropic diffusion filter and consider an adaptive method that correlate a nonlinear diffusion filter with a linear low-pass filter for the smoothing. In numerical experiments, we compare our proposed methods with some popular nonlinear diffusion models and the result show the promise of the adaptive procedure removes the noisy and preserves the edge effectively.
47
Singh, Rajat, and Devendra Singh Meena. "Study of image denoising using curvelet transform." Thesis, 2013. http://ethesis.nitrkl.ac.in/5164/1/109CS0633.pdf.
Full textAbstract:
The images usually bring different kinds of noise in the process of receiving, coding and
Transmission. In our implementation the Curvelet transform is used for de-noising of image.
Two digital implementations of the Curvelet transform the Unequally Spaced Fast Fourier
Transform (USFFT) and the Wrapping Algorithm are used to de-noise images degraded by
different types of noises such as Gaussian, Salt and Pepper, Random, Speckle and Poisson
noise. This thesis aims at the effect the Curvelet transform has in Curve-let shrinkage assuming
different types of noise models. A signal to noise ratios a measure of the quality of de-noising
was preferred. The experimental results show that the normal Curvelet shrinkage approach fails
to remove Poisson noise in medical images.
48
Patel, Kiran. "Hardware Architecture for Image Denoising Using DWT." Thesis, 2016. http://ethesis.nitrkl.ac.in/9299/1/2016_MT_KPatel.pdf.
Full textAbstract:
The use of multiresolution technique for time-frequency analysis of signal with high directionality has found its widespread acceptance in many digital image processing applications. The demand of high speed processing and time critical tasks required a time efficient hardware implementation of such techniques. In this thesis we design and implement a flexible hardware architecture for the 2D Discrete Wavelet Transform (DWT). This architecture can be configured to perform both the forward and inverse DWT for any DWT family, using fixed-point arithmetic and without auxiliary memory. The implementation of DWT can be done using convolution and Filter Bank (FB) based approach, but we adopt Lifting scheme architecture because of its effi- cient time complexity.
The design of the architecture is done in VHDL which provides concurrent execution of statements. Initially, the DWT core is modeled using MATLAB and parameterized in VHDL. The VHDL model is then simulated using ModelSim PE Student Edition 10.4a for the implementation of Cohen-DaubechiesFeauveau CDF 5/3 versions of the DWT. We have compared its efficacy with MATLAB based implemented method. Its potential is also demonstrated to perform image denoising task under additive white Gaussian noise (AWGN). The results indicate that both the implementation of CDF 5/3 hardware and denoising produce satisfactory results but with lower time complexity. The comparison of results is demonstrated using performance measure indices.
49
Panigrahi, Susant Kumar. "Image Denoising by Edge Preserved Curvelet Thresholding." Thesis, 2019. http://ethesis.nitrkl.ac.in/10040/1/2019_PhD_PSusantkumar_512EE102_Image.pdf.
Full textAbstract:
The limitations of imaging systems invariably add an undesirable component to the digital image referred as noise. Since modifying the imaging system is not always possible, denoising methods become an essential pre-processing step for many image processing applications. This thesis presents three novel contributions to the field of image denoising, while considering the phase as an indispensable component for restoration.
Phases Under AWGN: The phase of complex transforms like Fourier, Complex wavelet and Curvelet, of an image is more immune to noise than its magnitude. This thesis analyzes its immunity to additive white Gaussian noise (AWGN) both mathematically and quantitatively. We have derived noise sensitivity i.e. the rate of change of noisy image phase or magnitude with respect to AWGN magnitude. The results indicate that the magnitude of these transforms deteriorates faster than that of phase with increasing noise strength, while the Curvelet phase becomes more immune to noise compared with other transforms.
Denoising by Preserving the Phase: Denoising via Curvelet thresholding removes the coefficients below a threshold and loses signal residual in noise subspace. In effect, it produces ringing artifacts near edges. We found, the noise sensitivity of Curvelet phase – in contrast to its magnitude – reduces with the higher noise level. Thus, the magnitude of the coefficients below the threshold is estimated using Wiener filter (and joint bilateral filter in another method) at each scale and corresponding phase is preserved to recover the signal residual. We apply the Bilateral Filter (BF) at the finest scales to preserve the edges without any discontinuity. Further to reduce the ringing artifacts and to preserve efficiently the local structures like: edges, texturesand small details, the (Curvelet based) reconstructed image is post processed using the Guided Image Filter (GIF). The proposed method is tested on both artificial and natural images to prove its efficacy for denoising.
Denoising by Multi-Scale Hybrid Approach: This thesis presents another image denoising technique using a multiscale Non-Local Means (NLM) filtering combined with hard thresholding in the Curvelet domain. The inevitable ringing artifacts in the reconstructed image – due to thresholding – is further processed using GIF for better preservation of local structures like: edges, textures and small details. We decomposed the image into three different Curvelet scales including the approximation and the fine scale. The low frequency noise in the approximation sub-band and the edges with small textural details in the fine scale are processed independently using multiscale NLM filter. On the other hand, the hard thresholding in the remaining coarser scale is applied to separate the signal and the noise subspace. Experimental results on both grayscale and colour images indicate that the proposed approach is competitive at lower noise strength with respect to Peak Signal to Noise (PSNR) and Structural Similarity Index Measure (SSIM) measure and excels in performance at higher noise strength compared to several state-of-the-art algorithms.
50
Zhao, Hanqing. "Numerical Algorithms for Discrete Models of Image Denoising." Phd thesis, 2010. http://hdl.handle.net/10048/1165.
Full textAbstract:
In this thesis, we develop some new models and efficient algorithms for image denoising. The total variation model of Rudin, Osher, and Fatemi(ROF) for image denoising is considered to be one of the most successful deterministic denoising models. It exploits the non-smooth total variation (TV) semi-norm to preserve discontinuities and to keep the edges of smooth regions sharp. Despite its simple form, the TV semi-norm results in a strongly nonlinear Euler-Lagrange equation and poses computational challenge in solving the model efficiently. Moreover, this model produces so-called staircase effect. In this thesis, we propose several new algorithms and models to solve these problems. We study the discretized ROF model and propose a new algorithm which does not involve partial differential equations. Convergence of the algorithm is analyzed. Numerical results show that this algorithm is efficient and stable. We then introduce a denoising model which utilizes high-order difference to approximate piece-wise smooth functions. This model eliminates undesirable staircases, and improves both visual quality and signal-to-noise ratio. Our algorithm is generalized to solve the high-order models. A relaxation technique is proposed for the iteration scheme, aiming to accelerate our solution process. Finally, we propose a method combining total variation and wavelet packets to improve performance on texture-rich images. The ROF model is utilized to eliminate noise, and a wavelet packet transform is used to enhance textures. The numerical results show that the combinational method exploits the advantages of both total variation and wavelet packets.Mathematics