We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Embedding class information into local invariant features by low-dimensional retinotopic mapping.
- Authors
Raytchev, Bisser; Kikutsugi, Yuta; Tamaki, Toru; Kaneda, Kazufumi
- Abstract
In this paper, we propose a new general framework to obtain more distinctive local invariant features by projecting the original feature descriptors into low-dimensional feature space, while simultaneously incorporating also class information. In the resulting feature space, the features from different objects project to separate areas, while locally the metric relations between features corresponding to the same object are preserved. The low-dimensional feature embedding is obtained by a modified version of classical Multidimensional Scaling, which we call supervised Multidimensional Scaling (sMDS). Experimental results on a database containing images of several different objects with large variation in scale, viewpoint, illumination conditions and background clutter support the view that embedding class information into the feature representation is beneficial and results in more accurate object recognition.
- Subjects
OBJECT recognition (Computer vision); MULTIDIMENSIONAL scaling; DATABASES; ACCURACY; LIGHTING
- Publication
Machine Vision & Applications, 2013, Vol 24, Issue 2, p407
- ISSN
0932-8092
- Publication type
Article
- DOI
10.1007/s00138-012-0415-7