基于点特征的旋转图像匹配新方法  

New Algorithm of Image Rotation Matching Based on Feature Points

作　　者：吴定雪[1,2] 龚俊彬[1] 徐宏波[3] 田金文[1] 

机构地区：[1]华中科技大学图像识别与人工智能研究所,武汉430074 [2]黄冈师范学院计算机科学与技术学院,黄冈438000 [3]华中师范大学物理科学与技术学院,武汉430070

出　　处：《计算机科学》2009年第12期248-250,262,共4页Computer Science

基　　金：863国家重点基金项目(2007AA12z153)资助

摘　　要：图像匹配在模式识别、图像分析和计算机视觉中有着广泛的应用。图像匹配是将模板在参考图中逐像素移动,计算它们的灰度相似性,搜索相似性最大的位置。这种逐像素的搜索方法计算复杂度高。如果模板和参考图之间存在旋转,传统的匹配方法很难实时实现。提出了一种基于点特征的旋转图像的匹配方法,首先采用Harris角点检测算子提取图像的特征点,然后利用小面模型对特征点邻域进行拟合,提取特征点的旋转不变特征,最后利用特征点的旋转不变特征进行点集的匹配,获取图像的平移和旋转参数。该方法匹配结果准确,与传统的相关匹配方法相比计算复杂度很小,易于实时实现。Template matching has many applications in signal processing, image processing, pattern recognition, and video compressing. It fund a desired template in the large reference image by sliding the template window in a pixel-by-pixel basis, computing the degree of similarity between them, and searching position with the largest similarity measurement. It is computationally expensive to search for every possible position of the template window within the larger reference image. When having a rotation between the template and the reference image, the conventional template matching algorithm described above is not practical for real-time processing. In this paper, a point-matching algorithm was proposed to match the rotated template, which included： firstly, the feature points were detected by Harris detector, then the facet model was used to approximate locally the image intensity function,and the rotation-invariability of the feature point was extracted,finally, the transformation（translation and rotation） was obtained by matching feature points. Results have shown the efficacy of the proposed method.

关 键 词：图像匹配 点特征 角点 旋转不变性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]