DocumentCode :
2176068
Title :
A new paradigm for recognizing 3-D objects from range data
Author :
Ruiz-Correa, Salvador ; Shapiro, Linda G. ; Meila
Author_Institution :
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
fYear :
2003
fDate :
13-16 Oct. 2003
Firstpage :
1126
Abstract :
Most of the work on 3D object recognition from range data has used an alignment-verification approach in which a specific 3D object is matched to an exact instance of the same object in a scene. This approach has been successfully used in industrial machine vision, but it is not capable of dealing with the complexities of recognizing classes of similar objects. This paper undertakes this task by proposing and testing a component-based methodology encompassing three main ingredients: 1) a new way of learning and extracting shape-class components from surface shape information; 2) a new shape representation called a symbolic surface signature that summarizes the geometric relationships among components; and 3) an abstract representation of shape classes formed by a hierarchy of classifiers that learn object-class parts and their spatial relationships from examples.
Keywords :
feature extraction; image matching; image representation; learning by example; object recognition; robot vision; stereo image processing; 3D object recognition; Hilbert space; Mercel kernel; alignment-verification approach; automated inspection; autonomous navigation; industrial machine vision; robot vision; satellite image analysis; shape classes abstract representation; shape representation; shape-class components; support vector machine; surface shape information; symbolic surface signature; Character recognition; Computer vision; Dogs; Head; Humans; Layout; Object recognition; Rabbits; Shape measurement; Statistics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on
Conference_Location :
Nice, France
Print_ISBN :
0-7695-1950-4
Type :
conf
DOI :
10.1109/ICCV.2003.1238475
Filename :
1238475
Link To Document :
بازگشت