Locally Uniform Comparison Image Descriptor （局部图像描述符统一的比较）.pdf

Locally Uniform Comparison Image Descriptor Andrew Ziegler Eric Christiansen David Kriegman Serge Belongie Department of Computer Science and Engineering, University of California, San Diego amz@, echristiansen, kriegman, sjb@ Abstract Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors like BRIEF and related methods use pairwise compar- isons of pixel intensities in an image patch. We present an analysis of BRIEF and related approaches revealing that they are hashing schemes on the ordinal correla- tion metric Kendall’s tau. Here, we introduce Locally Uniform Comparison Image Descriptor (LUCID), a simple description method based on linear time permuta- tion distances between the ordering of RGB values of two image patches. LUCID is computable in linear time with respect to the number of pixels and does not require floating point computation. 1 Introduction Local image descriptors have long been explored in the context of machine learning and computer vision. There are countless applications that rely on local feature descriptors, such as visual regis- tration, reconstruction and object recognition. One of the most widely used local feature descriptors is SIFT which uses automatic scale selection, orientation normalization, and histograms of oriented gradients to achieve partial affine invariance [15]. SIFT is known for its versatility and reliable recognition performance, but these characteristics come at