A New Cross-Correlation Based Image Registration Method

Abstract

Image registration is a fundamental task for combining two or more images taken from different viewpoints, different times, or different sensors. It is a process of determining the point by point correspondence between two images from the same scene. The proposed image registration method uses the area-based approach to process image registration and the objective is to find the maximum similarity through the cross-correlation measure. Most cross-correlation methods are developed based on image intensities for the direct matching purpose. However, it is extremely sensitive to the intensity changes. To counteract illumination effect, the proposed method replaces the intensity with the gradient information, and this concept comes originally from the Hough transform that points having the same parameters and should be on the same line. These two parameters are combined as the similarity between images for image registration. The experimental results obtained by means of several test images illustrate the effectiveness of the proposed image registration method.