Title :
Fuzzy relations for feature-model correspondence in 3D object recognition
Author :
Walker, Ellen L.
Author_Institution :
Dept. of Comput. Sci., Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
This paper presents a new mechanism for determining feature correspondences for object recognition, based on fuzzy set theory. The new method applies unary and binary constraints from the model, taking uncertainty characteristics of the measurement process into consideration. Experiments with both unoccluded and occluded images show that the method selects an appropriate set of correspondences, especially when integrated with fuzzy perceptual grouping
Keywords :
feature extraction; fuzzy set theory; image matching; object recognition; uncertainty handling; 3D object recognition; binary constraints; feature-model correspondence; fuzzy perceptual grouping; fuzzy relations; fuzzy set theory; measurement process; occluded images; three dimensional object recognition; unary constraints; uncertainty; unoccluded images; Computer science; Feature extraction; Fuzzy reasoning; Fuzzy set theory; Fuzzy sets; Intelligent sensors; Intelligent systems; Object recognition; Sensor systems; Solid modeling;
Conference_Titel :
Fuzzy Information Processing Society, 1996. NAFIPS., 1996 Biennial Conference of the North American
Conference_Location :
Berkeley, CA
Print_ISBN :
0-7803-3225-3
DOI :
10.1109/NAFIPS.1996.534698
