图像匹配几种常见算法外文文献.docVIP

Systems Design Engineering, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, Canada N2L 3G1  Abstract An interesting problem in pattern recognition is that of image registration, which plays an important role in many vision-based recognition and motion analysis applications. Of particular interest among registration problems are multimodal registration problems, where the images exist in different feature spaces. State-of-the-art phased-based approaches to multimodal image registration methods have provided good accuracy but have high computational cost. This paper presents a fast phase-based approach to registering multimodal images for the purpose of initial coarse-grained registration. This is accomplished by simultaneously performing both globally exhaustive dynamic phase sub-cloud matching and polynomial feature space transformation estimation in the frequency domain using the fast Fourier transform (FFT). A multiscale phase-based feature extraction method is proposed that determines both the location and size of the dynamic sub-clouds being extracted. A simple outlier pruning based on resampling is used to remove false keypoint matches. The proposed phase-based approach to registration can be performed very efficiently without the need for initial estimates or equivalent keypoints from both images. Experimental results show that the proposed method can provide accuracies comparable to the state-of-the-art phase-based image registration methods for the purpose of initial coarse-grained registration while being much faster to compute. Keywords: Image registration; Phase; Fast Fourier transform; Multimodal; Keypoints; Dynamic sub-clouds Article Outline 1. Introduction 2. Multimodal registration problem 3. Previous work 4. Proposed registration algorithm 4.1. Keypoint detection and sub-cloud size estimation 4.2. Phase sub-cloud extraction 4.3. Simultaneous sub-cloud matching and feature space transformation estimation 4.4. Solving th