Picking the best DAISY

S Winder, Gang Hua, Matthew A Brown

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

242 Citations (SciVal)
246 Downloads (Pure)


Local image descriptors that are highly discriminative, computational efficient, and with low storage footprint have long been a dream goal of computer vision research. In this paper, we focus on learning such descriptors, which make use of the DAISY configuration and are simple to compute both sparsely and densely. We develop a new training set of match/non-match image patches which improves on previous work. We test a wide variety of gradient and steerable filter based configurations and optimize over all parameters to obtain low matching errors for the descriptors. We further explore robust normalization, dimension reduction and dynamic range reduction to increase the discriminative power and yet reduce the storage requirement of the learned descriptors. All these enable us to obtain highly efficient local descriptors: e.g, 13.2% error at 13 bytes storage per descriptor, compared with 26.1% error at 128 bytes for SIFT.
Original languageEnglish
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009)
Number of pages8
ISBN (Print)9781424439928, 9781424439911
Publication statusPublished - 13 Aug 2009
EventCVPR 2009: IEEE Conference on Computer Vision and Pattern Recognition, 2009 - Miami
Duration: 20 Jun 200925 Jun 2009


ConferenceCVPR 2009: IEEE Conference on Computer Vision and Pattern Recognition, 2009


Dive into the research topics of 'Picking the best DAISY'. Together they form a unique fingerprint.

Cite this