Learning Local Image Descriptors

Simon A J Winder, Matthew Brown

Research output: Contribution to conferencePaperpeer-review

279 Citations (SciVal)


In this paper we study interest point descriptors for image matching and 3D reconstruction. We examine the building blocks of descriptor algorithms and evaluate numerous combinations of components. Various published descriptors such as SIFT, GLOH, and Spin images can be cast into our framework. For each candidate algorithm we learn good choices for parameters using a training set consisting of patches from a multi-image 3D reconstruction where accurate ground-truth matches are known. The best descriptors were those with log polar histogramming regions and feature vectors constructed from rectified outputs of steerable quadrature filters. At a 95% detection rate these gave one third of the incorrect matches produced by SIFT.
Original languageEnglish
Publication statusPublished - Jun 2007
EventCVPR '07: IEEE Conference on Computer Vision and Pattern Recognition, 2007 - Minneapolis
Duration: 17 Jun 200722 Jun 2007


ConferenceCVPR '07: IEEE Conference on Computer Vision and Pattern Recognition, 2007


Dive into the research topics of 'Learning Local Image Descriptors'. Together they form a unique fingerprint.

Cite this