Visual Manifold Sensing

Irina Burciu, Adrian Ion-Margineanu, Thomas Martinetz, Erhardt Barth

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.


OriginalspracheEnglisch
TitelHuman Vision and Electronic Imaging XIX
Redakteure/-innenBernice E. Rogowitz, Thrasyvoulos N. Pappas, Huib de Ridder
Seitenumfang8
Band90141B
Herausgeber (Verlag)SPIE
Erscheinungsdatum25.02.2014
Seiten9014 - 9014 - 8
ISBN (Print)9780819499318
DOIs
PublikationsstatusVeröffentlicht - 25.02.2014
VeranstaltungHuman Vision and Electronic Imaging 2014 - San Francisco, California, USA / Vereinigte Staaten
Dauer: 03.02.201406.02.2014
http://hvei.eecs.northwestern.edu/past.html

Zitieren