A Novel Histogram Based Robust Image Registration Technique

TL;DR

This paper introduces a histogram-based automatic image registration method that combines multiple segmentations and object characterization to achieve robust, subpixel accuracy in aligning remotely sensed images with differences in rotation and translation.

Contribution

The proposed approach uniquely integrates multiple image segmentations and object features for improved robustness and accuracy in image registration tasks.

Findings

Achieves subpixel registration accuracy.

Effectively handles images with rotation and translation differences.

Demonstrates robustness through combined segmentation and object characterization.

Abstract

In this paper, a method for Automatic Image Registration (AIR) through histogram is proposed. Automatic image registration is one of the crucial steps in the analysis of remotely sensed data. A new acquired image must be transformed, using image registration techniques, to match the orientation and scale of previous related images. This new approach combines several segmentations of the pair of images to be registered. A relaxation parameter on the histogram modes delineation is introduced. It is followed by characterization of the extracted objects through the objects area, axis ratio, and perimeter and fractal dimension. The matched objects are used for rotation and translation estimation. It allows for the registration of pairs of images with differences in rotation and translation. This method contributes to subpixel accuracy.