Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor  

作　　者：Jian Chen, Jie Tian Institute of Automation, Chinese Academy of Science, Beijing 100080, China 

出　　处：《Progress in Natural Science:Materials International》2009年第5期643-651,共9页自然科学进展·国际材料（英文版）

基　　金：supported by the National Basic Research Program of China (Grant No.2006CB705700);the grant from Changjiang Scholars and Innovative Research Team in University (PCSIRT) (IRT0645);CAS Hundred Talents Program,CAS Scientific Research Equipment Develop Program (YZ0642,YZ200766);High-tech Research and Development Program of China (2006AA04Z216);the Joint Research Fund for Overseas Chinese Young Scholars (30528027);National Natural Science Foundation of China (30672690,30600151,30500131,60532050);Beijing Natural Science Fund (4071003)

摘　　要：The purpose of image registration is to spatially align two or more single-modality images taken at different times, or several images acquired by multiple imaging modalities. Intensity-based registration usually requires optimization of the similarity metric between the images. However, global optimization techniques are too time-consuming, and local optimization techniques frequently fail to search the global transformation space because of the large initial misalignment of the two images. Moreover, for large non-overlapping area registration, the similarity metric cannot reach its optimum value when the two images are properly registered. In order to solve these problems, we propose a novel Symmetric Scale Invariant Feature Transform (symmetric-SIFT) descriptor and develop a fast multi-modal image registration technique. The proposed technique automatically generates a lot of highly distinctive symmetric-SIFT descriptors for two images, and the registration is performed by matching the corresponding descriptors over two images. These descriptors are invariant to image scale and rotation, and are partially invariant to affine transformation. Moreover, these descriptors are symmetric to contrast, which makes it suitable for multi-modal image registration. The proposed technique abandons the optimization and similarity metric strategy. It works with near real-time performance, and can deal with the large non-overlapping and large initial misalignment situations. Test cases involving scale change, large non-overlapping, and large initial misalignment on computed tomography (CT) and magnetic resonance (MR) datasets show that it needs much less runtime and achieves better accuracy when compared to other algorithms.The purpose of image registration is to spatially align two or more single-modality images taken at different times, or several images acquired by multiple imaging modalities. Intensity-based registration usually requires optimization of the similarity metric between the images. However, global optimization techniques are too time-consuming, and local optimization techniques frequently fail to search the global transformation space because of the large initial misalignment of the two images. Moreover, for large non-overlapping area reg- istration, the similarity metric cannot reach its optimum value when the two images are properly registered. In order to solve these problems, we propose a novel Symmetric Scale Invariant Feature Transform （symmetric-SIFT） descriptor and develop a fast multi-modal image reg- istration technique. The proposed technique automatically generates a lot of highly distinctive symmetric-SIFT descriptors for two images, and the registration is performed by matching the corresponding descriptors over two images. These descriptors are invariant to image scale and rotation, and are partially invariant to affine transformation. Moreover, these descriptors are symmetric to contrast, which makes it suitable for multi-modal image registration. The proposed technique abandons the optimization and similarity metric strategy. It works with near real-time performance, and can deal with the large non-overlapping and large initial misalignment situations. Test cases involving scale change, large non-overlapping, and large initial misalignment on computed tomography （CT） and magnetic resonance （MR） datasets show that it needs much less runtime and achieves better accuracy when compared to other algorithms.

关 键 词：Symmetric-SIFT MULTI-MODAL REGISTRATION Keypoint MATCHING 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP311.13[自动化与计算机技术—计算机科学与技术]