An automatic registration and mosaicking system based on contour features and wavelet transform for remote sensing images

Image registration is an inevitable problem arising in many image-processing applications whenever two or more images of the same scene have to be compared pixel by pixel. The increased volume of satellite images has reinforced the need for automatic image registration methods. In this paper, two new feature-based approaches to automated image-to-image registration are presented. The characteristic of the first approach is that it combines an invariant moment shape descriptor with improved chain-code matching to establish correspondences between the potentially matched regions detected from the two images. This method works well for image pairs in which the contour information is well preserved, such as the optical images from Landsat and Spot satellites. For the registration of the optical images with synthetic aperture radar (SAR) images, we propose another method based on the wavelet transform, this second method uses spectral information of the images and their local wavelet transform modulus maxima to extract a set of control points. The experimental result demonstrates the robustness, efficiency and accuracy of the two algorithms.