FAIR: Towards A New Feature for Affinely-Invariant Recognition

In this paper we propose the first version of FAIR, a low-dimensional image neighborhood descriptor that shows performance comparable to SIFT introduced by Lowe. The dimension of FAIR we tested is 30, compared to the dimension of 128 in SIFT. Sensitivity of the FAIR descriptor to skew, rotation, image blur and noise is similar to SIFT. FAIR shows better localization in scale-space than SIFT. Several extensions of FAIR that could improve its performance are discussed.

• Type: Conference
• Year: 2006
• Where: ICPR
• Authors: Martin Matousek, Radim Sára
• Keywords: Computer Vision, FAIR Descriptor, ICPR 2006, Image Neighborhood Descriptor