Image registration is an important and fundamental task in image processing used to match two different images. Given two or more different images to be registered, image registration estimates the parameters of the geometrical transformation model that maps the sensed images back to its reference image. A feature-based approach to automated imageto-image registration is presented. The characte...

Locating the calibration markers of a chessboard is a prerequisite step to camera calibration. The efficiency and accuracy of this step has a crucial influence to the final results. This paper presents an automatic method for detection and location the internal corners of black and white squares by using Multi-Radon Transform (MRT) and image segmentation methods. The whole procedure mainly incl...

This thesis contains three articles. The first two concern inversion and local injectivity of the weighted Radon transform in the plane. The third paper concerns two of the key results from compressive sensing. In Paper A we prove an identity involving three singular double integrals. This is then used to prove an inversion formula for the weighted Radon transform, allowing all weight functions...

An algorithm from Radon transform to obtain local tomography from multiple CT slices for localized 3D reconstruction is developed. The proposed method uses Radon transform to obtain projections for a region of interest. Reconstructing a particular cross section of a human body using local data will significantly reduce Xray exposure during imaging. Image reconstruction is performed using filter...

Two theorems are presented for wavelet decompositions of the two-dimensional Radon transform. The first theorem establishes an upper error bound in L-norm between the Radon transform and its wavelet approximation whose coefficients at different scales are estimated from Radon data acquired at corresponding sampling rates. The second theorem gives an estimate of the accuracy of a local image rec...

Analogous to the radar Doppler spectrum for coherent processing, the concept of a Radon spectrum that is a kind of normalised Radon transform is proposed and used for radar non-coherent detection. One advantage of using the Radon transform for non-coherent processing is that integration in all directions is considered, and hence range migration of moving targets is not a concern. The detection ...