In this paper, we address the challenging problem of recovering the defocus map from a single image. We present a simple yet effective approach to estimate the amount of spatially varying defocus blur at edge locations. The input defocused image is re-blurred using a Gaussian kernel and the defocus blur amount can be obtained from the ratio between the gradients of input and re-blurred images. ...

Identification of motion parameters is an important issue in image restoration of a linear motion blur. Based on the human visual-motion sensing properties, an integrated approach with some known image processing techniques is proposed to the estimation of the direction and extent of motion on a linear motion blurred image. Experimental results confirm the feasibility of our approach. key words...

CONTENTS 1. Introduction 2. Image and blur models 3. Maximum likelihood (ML) parameter identification 3.1. Formulation 3.2. Constraints on the unknown parameters 4. ML parameter identification via the expectation-maximization (EM) algorithm 4.1. The EM algorithm in the linear Gaussian case 4.2. Choices of complete data 4.2.1. {x,y} as the complete data 4.2.2. {x,v} as the complete data Abstract...

Image blur kernel classification and parameter estimation are critical for blind image deblurring. Current dominant approaches use handcrafted blur features that are optimized for a certain type of blur, which is not applicable in real blind deconvolution application when the Point Spread Function (PSF) of the blur is unknown. In this paper, a Twostage system using Deep Neural Network (DNN) and...

Shooting a real world image with a camera through an optical device gives a 2-D image where at least some parts are affected by a blur and noise. Images can be blurred by atmospheric turbulence, relative motion between sensors and objects, longer exposures, and so on, but the exact cause of blurring may be unknown. Restoration of blurred noisy images (Spiros et al., 2009; 2010; Su et al., 2007)...

Pattern recognition and registration are integral elements of computer vision, which considers image patterns. This thesis presents novel blur, and combined blur and geometric invariant features for pattern recognition and registration related to images. These global or local features are based on the Fourier transform phase, and are invariant or insensitive to image blurring with a centrally s...

Adaptation to a blurred image causes a physically focused image to appear too sharp, and shifts the point of subjective focus toward the adapting blur, consistent with a renormalization of perceived focus. We examined whether and how this adaptation normalizes to differences in blur between the two eyes, which can routinely arise from differences in refractive errors. Observers adapted to image...

The image blur and binocular disparity of a 3D scene point both increase with distance in depth away from fixation. Perceived depth from disparity has been studied extensively and is known to be most precise near fixation. Perceived depth from blur is much less well understood. A recent experiment (Held, R. T, Cooper, E. A., & Banks, M. S. (2012). Current Biology, 22, 426-431) which used a volu...

Face recognition is the biometric identification by scanning a person's face and matching it against a library of known faces. The Issues in Face recognition include image degradation due to blur and variations in appearance due to illumination. Blur refers to the less sharpness or unclearness in images whereas Illumination refers to the placement of light sources in images. Our approach deals ...