结合角点特征与SIFT特征的加速图像匹配

Combining Corner and SIFT Featrues to Accelerate Image Matching

利用关键点寻找不同图像之间的一致性是很多图像处理和计算机视觉应用中的一个关键步骤。由于图像中巨量的关键点,因此特征的快速匹配成为了一个瓶颈。文中提出了一种对特征点进行分类比较的方法来加速特征匹配。首先可将SIFT特征分为两类,极大值SIFT特征和极小值SIFT特征;其次是将SIFT特征和传统角点特征相结合提取特征点并按照角点特征进行分类。实验表明,这种方法在保持原有鲁棒性和精度的情况下,可以较大提高特征匹配速度。

The use of keypoints to find correspondences across multiple images is a key step in many image processing and computer vision applications. Due to the large numbers of keypoints in an image,the feature matching rapidly becomes a bottleneck. In this paper,a novel method is presented to accelerate features matching by making comparisons only between the features of the same types. The first one is based on splitting the SIPT features into two types,Maxima-SIFT and Minima-SIFT features. In the second one,the SIFr feature combines the traditional comer-like features which use moment-derived comer patterns to extract keypoints and split sift features into different types use comer patterns. The presented experimental results show that the method has a big acceleration in the features matching performance compared to the original one without lose a noticeable precision and robustness.