In this paper we introduce and analyze a set of regularization expressions based on self-similarity properties of images in order to address the classical inverse problem of image denoising and the ill-posed inverse problem of single-frame image zooming. The regularization expressions introduced are constructed using either the fractal image transform or the newly developed “Nonlocal-means (NL-...

In order to scale video image real-timely, a GPU-aided parallel interpolation algorithm was proposed. Catmull-Rom Spline algorithm for image zooming was reformed into SIMD (Single instruction, multiple data) mode according to CUDA programming model. Re-sampling of each pixel was completed by a GPU thread. Hence, time-consuming re-sampling procedure of the whole zooming process were handled by p...

In this paper we present a Bayesian image zooming/super-resolution algorithm based on a patch based representation. We work on a patch based model with overlap and employ a Locally Linear Embedding (LLE) based approach as our data fidelity term in the Bayesian inference. The image prior imposes continuity constraints across the overlapping patches. We apply an error back-projection technique, w...

The purpose of this thesis is to discuss digital image resolution enhancement by variational methods and the associated computational issues. Two problems related to the basic zooming problem are also studied: super-resolution and quantized deconvolution. Digital zooming is important for mundane computing activities such as web browsing as well as sophisticated applications like satellite image...

We describe a formative evaluation of a prototype image browser based on flip zooming, a focus+context visualisation technique. The technique was contrasted with two other methods to view images on the Web. The evaluation showed that users appreciated the overview that the flip zooming prototype provided, although some found the display confusing.

In contemporary image databases one finds many images with the same image content but perturbed by zooming, scaling, rotation etc. For the purpose of image recognition in such databases we employ features based on statistics stemming from fractal transforms of gray-scale images. We show how the features derived from these statistical aspects can be made invariant to zooming or rescaling. A feat...

High-resolution image mosaics construction is one of the significant topics of research in the fields of computer vision, image processing, and computer graphics. Video mosaics contain enormous valuable information but when analyzing, searching or browsing a video, redundancy between frames creates problem. Therefore it is more suitable to bring together all the frames of a shot into one single...

We present a novel technique for calibrating a zooming camera based on the invariance properties of the Normalised Image of the Absolute Conic (NIAC). We show that the camera parameters independent of position, orientation and zooming are determined uniquely by the NIAC, and we exploit these invariance properties to develop a stratified calibration method that decouples the calibration paramete...