Evaluation of sets of oriented and non-oriented receptive fields as local descriptors
Author(s)
Yokono, Jerry Jun
Poggio, Tomaso
Date Issued
March 24, 2004
Series/Report no.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
Abstract
Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. We propose a performance criterion for a local descriptor based on the tradeoff between selectivity and invariance. In this paper, we evaluate several local descriptors with respect to selectivity and invariance. The descriptors that we evaluated are Gaussian derivatives up to the third order, gray image patches, and Laplacian-based descriptors with either three scales or one scale filters. We compare selectivity and invariance to several affine changes such as rotation, scale, brightness, and viewpoint. Comparisons have been made keeping the dimensionality of the descriptors roughly constant. The overall results indicate a good performance by the descriptor based on a set of oriented Gaussian filters. It is interesting that oriented receptive fields similar to the Gaussian derivatives as well as receptive fields similar to the Laplacian are found in primate visual cortex.
Subjects
AI
local descriptor
steerable filter
Gaussian derivatives
selectivity,invariance
Persistent DSpace Link
