The Log Polar Transformation for Rotation Invariant Image Registration of Aerial Images

Aerial image registration requires a high degree of precision. To improve the feature-based registration accuracy, this paper proposes a novel Log-Polar Transform (LPT) based image registration. Instead of using the whole image in the conventional method, feature points are used here, which reduces the computational time. It is not important how the image patch is rotated for rotation invariance. The key is focusing on the feature points. So a circular image patch is used, instead of using square image patches as used in conventional methods. In the existing techniques of registration always do FFT first and then Log-Polar Transformation (LPT). In this proposed technique does LPT first and then the FFT. The proposed technique contains four steps. First, feature points are selected in both the reference image and the sensed image with corner detector. Secondly, using feature point positions as centers image patches are created. Circular image patches are cropped choosing a feature point as center. Then the circular images are transformed from Cartesian co-ordinates to Log-Polar coordinates. Next, the LPT images are dealt using phase correlation. Experimental results demonstrate the reliability and rotation invariance of the proposed