With the increased presence of image-based data in modern applications, the need for robust methods of image denoising grows greater. The work presented herein considers two of the most ubiquitous approaches towards image denoising: variational and non-local methods. The effectiveness of these methods is assessed using quantitatively using peak signal-to-noise ratio and structural similarity index measure metrics. This study employs ��−means clustering, an unsupervised machine learning algorithm, to isolate the most dominant cluster centroids within the incoming data and propose the introduction of a new adaptive parameter into the non-local means framework. Motivated by the fact that a majority of discrepancies between clean and denoised images occur at feature edges, this study examines several convolution-based edge detection methods to isolate relevant feature. The resultant gradient and edge information is used to further parameterize the ��−means non-local method. An additional hybrid method involving the combined contributions of variational and ��−means non-local denoising is proposed, with the weighting determined by edge intensities. This method outperforms the other methods outlined in the study, both conventional and newly presented.

No description available.

No description available.

No description available.

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.

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.

The aim of this project is to keep the x-ray exposure of the patient as low as reasonably achievable while improving the diagnostic image quality for the radiologist. The means to achieve these goals is to develop and evaluate an ecient adaptive ltering (denoising/image enhancement) method that fully explores true 4D image acquisition modes. The proposed prototype system uses a novel lter set having directional lter responses being monomials. The monomial lter concept is used both for estimation of local structure and for the anisotropic adaptive ltering. Initial tests on clinical 4D CT-heart data with ECG-gated exposure has resulted in a signicant reduction of the noise level and an increased detail compared to 2D and 3D methods. Another promising feature is that the reconstruction induced streak artifacts which generally occur in low dose CT are remarkably reduced in 4D.

No description available.

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

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.