Automatic Image Registration through Histogram-Based Image Segmentation

摘要

Image registration is the process of transforming different sets of data into one coordinate system. Automatic image registration is still an actual challenge in several fields like computer vision and remote sensing applications. In this project, a method for automatic image registration through histogram-based image segmentation is proposed. This new approach mainly consists in combining the pair of images to be registered are segmented, according to a relaxation parameter on the histogram modes delineation (which itself is a new approach), followed by a consistent characterization of the extracted objects through the objects area, ratio between the axis of the adjust ellipse, perimeter and fractal dimension and a robust statistical based procedure for objects matching. The main aim of this proposed methodology is illustrated to simulated rotation and translation. The first dataset consists in a photograph and a rotated and shifted version of the same photograph, with different levels of added noise. This allows for the registration of pairs of images with differences in rotation and translation.