Photographs of text documents taken by hand-held cameras can be easily degraded by camera motion during exposure. In this paper, we propose a new method for blind deconvolution of document images. Observing that document images are usually dominated by small-scale high-order structures, we propose to learn a multi-scale, interleaved cascade of shrinkage fields model, which contains a series of ...

Blind image deconvolution, a technique for obtaining restored as well the blur kernel from an inexact image. This research uses spatial characteristics to tackle problem of blind deconvolution. To work, proposed method does not necessitate prior information about kernel. Many applications, such remote sensing, astronomy, and medical X-ray imaging, deconvolution algorithms. study used maximum po...

We propose to represent classified datasets as a feature graph storing different graphical models and attributes for each feature. This graph allows us to render each feature according to its own characteristics. In addition, we show that various features of the graph storing volume information at different resolution levels can be rendered together using a view-aligned splatting method. Moreov...

This study proposes a super-resolution (SR) method for terahertz time-domain spectroscopy (THz-TDS) images, combining convolutional neural network (CNN) and mathematical degradation model. The model considers three possible factors affecting the quality of THz images: blur kernel, noise, down-sampler. Specifically, kernel characterizes continual change image extent with imaging distance. design...

We propose to represent classified datasets as a feature graph storing different graphical models and attributes for each feature. This graph allows us to render each feature according to its own characteristics. In addition, we show that various features of the graph storing volume information at different resolution levels can be rendered together using a view-aligned splatting method. Moreov...

The blurred image blind restoration is a difficult problem of image processing. The key is the estimation of the Point Spread Function and non-blind deconvolution algorithm. In this paper, we propose a fast robust algorithm based on radon transform-domain to determine the blur kernel function. Then the blurred images are restored by using a modified fast non-blind deconvolution method based on ...

Acoustic micro imaging has been proven to be sufficiently sensitive for micro defect detection. In this study, we propose a sparse reconstruction method for acoustic micro imaging. A finite element model with a micro defect is developed to emulate the physical scanning. Then we obtain the point spread function, a blur kernel for sparse reconstruction. We reconstruct deblurred images from the ov...

In many imaging systems, the point spread function (PSF) is non-stationary. Usually a computation-intensive iterative algorithm is used to de-blur the non-stationary PSF. This paper presents a new idea of using a non-iterative method to compensate for the spatially variant PSF. This method first further blurs the image with a non-stationary kernel so that the resultant image has a stationary PS...

To peripheral vision, a pair of physically different images can look the same. Such pairs are metamers relative to each other, just as physically-different spectra light perceived same color. We propose real-time method compute such ventral for foveated rendering where, in particular near-eye displays, largest part framebuffer maps periphery. This improves quality over state-of-the-art foveatio...