Disambiguation techniques for recognition in large databases and for under-constrained reconstruction

Daphna Weinshall*, Michael Werman

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations

Abstract

When computing 3D interpretations of noisy 2D images, many interpretations are often plausible. We describe a general framework for resolving such ambiguities in object recognition and reconstruction using maximum likelihood estimation. To this end we define measures of likelihood and stability of interpretations. These measures also give a practical way to evaluate how 'generic' views are, and identify 'characteristics' views. To demonstrate the usefulness and generality of this framework, we computed the proposed stability and likelihood measures using 4 different kinds of image matching algorithms, matching: (1) feature points, (2) angles, (3) occluding contours of smooth surfaces, and (4) shaded images of smooth surfaces.

Original languageAmerican English
Pages425-430
Number of pages6
StatePublished - 1995
EventInternational Symposium on Computer Vision, ISCV'95, Proceedings - Coral Gables, FL, USA
Duration: 21 Nov 199523 Nov 1995

Conference

ConferenceInternational Symposium on Computer Vision, ISCV'95, Proceedings
CityCoral Gables, FL, USA
Period21/11/9523/11/95

Fingerprint

Dive into the research topics of 'Disambiguation techniques for recognition in large databases and for under-constrained reconstruction'. Together they form a unique fingerprint.

Cite this