We consider the problem of non-blind deconvolution of images corrupted by a blur that is not accurately known. We propose a method that exploits dictionary-based image priors and non Gaussian noise models to improve deblurring accuracy in the presence of an inexact blur. The proposed image priors express each image patch as a linear combination of atoms from a dictionary learned from patches ex...

Super Resolution (SR) image can be obtained from a set of Low Resolution (LR) images with noise and blur. The main object of Super Resolution is to get high resolution, high quality image from Low Resolution images. To remove the blur and noises caused by the imaging system as well as recover information, restoration techniques are used. Super resolution imaging processes one or more low resolu...

The two eyes of an individual routinely differ in their optical and neural properties, yet percepts through either eye remain more similar than predicted by these differences. Little is known as to how the brain resolves this conflicting information. Differences in visual inputs from the two eyes have been studied extensively in the context of binocular vision and rivalry [1], but it remains un...

Title of thesis: BLUR AND ILLUMINATIONINVARIANT FACE RECOGNITION VIA SET-THEORETIC CHARACTERIZATION Priyanka Vageeswaran, Master of Science, 2013 Thesis directed by: Professor Rama Chellappa Department of Electrical and Computer Engineering In this thesis we address the problem of unconstrained face recognition from remotely acquired images. The main factors that make this problem challenging a...

In this paper, an image restoration algorithm is proposed to identify nonlinear and noncausal blur funclon using artificial neural networks. Image and degradation processes include both linear and nonlinear phenomena. The proposed neural network model, which combines an adaptive auto-associative network with a random Gaussian process, is used to restore the blurred image and blur function, simu...

The quality of images may be severely degraded in various situations such as imaging during motion, sensing through a diffusive medium, and low signal to noise. Often in such cases, the ideal un-degraded image is not available (no reference exists). This paper overviews past methods that dealt with no-reference (NR) image quality assessment, and then proposes a new NR method for the identificat...

Different blur invariant descriptors have been proposed so far, which are either in the spatial domain or based on the properties available in the moment domain. In this paper, a frequency framework is proposed to develop blur invariant features that are used to deconvolve a degraded image caused by a Gaussian blur. These descriptors are obtained by establishing an equivalent relationship betwe...

Camera motion introduces spatially varying blur due to the depth changes in 3D world. This work investigates scene configurations where such is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent blur. The (forward) produces realistic from single image, map, and trajectory. Furthermore, we utilize ICB model, combined w...

In this paper, a no reference blur image quality metric based on wavelet transform is presented. As blur affects specially edges and image fine details, most blur estimation algorithms, are based primarily on an adequate edge detection methods. Here we propose a new approach by analyzing edges through a multi-resolution decomposition. The ability of wavelets to extract the high frequency compon...

Obtained images through imaging systems are considered as degraded versions of the original view. Computed Tomography (CT) images have different types of degradations such as noise, blur and contrast imperfections. This paper handles the issue of deblurring CT medical images affected by Gaussian blur. Image deblurring is the procedure of decreasing the blur amount and grant the filtered image w...