Czech Pattern Recognition Society Feature point detection in multiframe images

Abstract Feature point (FP) detection is an important pre-processing step in image registration, data fusion, objec-t recognition and in many other tasks. This paper deals with multiframe FP detection, i.e. detection in two or more images of the same scene which are supposed to be blurred, noisy, rotated and shifted with respect to each other. We present a new method invariant under rotation that can handle differ-ently blurred images. Thanks to this, the point sets extracted from different frames have relatively high number of common elements. This property is highly desirable for further multi-frame processing. The performance of the method is demon-strated experimentally on satellite images and application on medical data is