Stable bounded canonical sets and image matching
2005 (English)In: ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS / [ed] Rangarajan, A; Vemuri, B; Yuille, AL, BERLIN: SPRINGER-VERLAG BERLIN , 2005, Vol. 3757, 316-331 p.Conference paper (Refereed)
A common approach to the image matching problem is representing images as sets of features in some feature space followed by establishing correspondences among the features. Previous work by Huttenlocher and Ullman  shows how a similarity transformation - rotation, translation, and scaling - between two images may be determined assuming that three corresponding image points are known. While robust, such methods suffer from computational inefficiencies for general feature sets. We describe a method whereby the feature sets may be summarized using the stable bounded canonical set (SBCS), thus allowing the efficient computation of point correspondences between large feature sets. We use a notion of stability to influence the set summarization such that stable image features are preferred.
Place, publisher, year, edition, pages
BERLIN: SPRINGER-VERLAG BERLIN , 2005. Vol. 3757, 316-331 p.
, LECTURE NOTES IN COMPUTER SCIENCE, ISSN 0302-9743 ; 3757
IdentifiersURN: urn:nbn:se:kth:diva-42695DOI: 10.1007/11585978_21ISI: 000234193000021ScopusID: 2-s2.0-33646581034ISBN: 3-540-30287-5OAI: oai:DiVA.org:kth-42695DiVA: diva2:447442
5th International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition. St Augustine, FL. NOV 09-11, 2005
QC 201110112011-10-122011-10-112011-10-12Bibliographically approved