DocumentCode
699677
Title
Object recognition methods based on transformation covariant features
Author
Matas, Jiri ; Obdrzalek, Stepan
Author_Institution
Center for Machine Perception, Czech Tech. Univ., Prague, Czech Republic
fYear
2004
fDate
6-10 Sept. 2004
Firstpage
1721
Lastpage
1728
Abstract
Methods based on distinguished regions (transformation covariant detectable patches) have achieved considerable success in a range of object recognition, retrieval and matching problems, in still images and videos. We review the state-of-the-art, describe relationship to other recognition methods, analyse their strengths and weaknesses, and present examples of successful applications.
Keywords
covariance analysis; feature extraction; image matching; image retrieval; object recognition; object matching problem; object recognition method; object retrieval; still image; still video; transformation covariant features; Abstracts; Adaptation models; Complexity theory; Detectors; Geometry; Object recognition; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Conference, 2004 12th European
Conference_Location
Vienna
Print_ISBN
978-320-0001-65-7
Type
conf
Filename
7080207
Link To Document