Share Email Print

Proceedings Paper

Visual manifold sensing
Author(s): Irina Burciu; Adrian Ion-Mărgineanu; Thomas Martinetz; Erhardt Barth
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a novel method, Manifold Sensing, for the adaptive sampling of the visual world based on manifolds of increasing but low dimensionality that have been learned with representative data. Because the data set is adapted during sampling, every new measurement (sample) depends on the previously acquired measurements. This leads to an efficient sampling strategy that requires a low total number of measurements. We apply Manifold Sensing to object recognition on UMIST, Robotics Laboratory, and ALOI benchmarks. For face recognition, with only 30 measurements - this corresponds to a compression ratio greater than 2000 - an unknown face can be localized such that its nearest neighbor in the low-dimensional manifold is almost always the actual nearest image. Moreover, the recognition rate obtained by assigning the class of the nearest neighbor is 100%. For a different benchmark with everyday objects, with only 38 measurements - in this case a compression ratio greater than 700 - we obtain similar localization results and, again, a 100% recognition rate.

Paper Details

Date Published: 25 February 2014
PDF: 8 pages
Proc. SPIE 9014, Human Vision and Electronic Imaging XIX, 90141B (25 February 2014); doi: 10.1117/12.2043012
Show Author Affiliations
Irina Burciu, Univ. of Lübeck (Germany)
Adrian Ion-Mărgineanu, Univ. of Lübeck (Germany)
Thomas Martinetz, Univ. of Lübeck (Germany)
Erhardt Barth, Univ. of Lübeck (Germany)

Published in SPIE Proceedings Vol. 9014:
Human Vision and Electronic Imaging XIX
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Huib de Ridder, Editor(s)

© SPIE. Terms of Use
Back to Top