Projection-based image registration algorithms use the sum of the pixel values along a given axis of an image to detect spatial changes in temporally separated images. These algorithms have been shown to be computationally efficient and effective for aligning temporally separated images and for visually detecting sensor motion. Registering images via projections has also been shown as a method for overcoming registration errors caused by the presence of fixed pattern noise. This paper describes a method that exploits the statistical properties of images with significant autocorrelation to improve the performance of projection-based image registration algorithms. The algorithm is shown to operate in low SNR conditions and to significantly improve registration performance by as much as a factor of 4 in mean squared error over existing projection-based registration algorithms at a minimal computational cost.
Improving the Performance of Projection-Based Image Registration
2008-03-01
2252402 byte
Conference paper
Electronic Resource
English
Projection registration applied to nondestructive testing
British Library Online Contents | 2010
|Mesh Topological Optimization for Improving Piecewise-Linear Image Registration
British Library Online Contents | 2010
|European Patent Office | 2021
|Curvature Based Image Registration
British Library Online Contents | 2003
|IMAGE PROJECTION DEVICE, IMAGE PROJECTION METHOD, AND IMAGE PROJECTION PROGRAM
European Patent Office | 2017
|