Title :
Pose clustering on constraints for object recognition
Author :
Chakravarthy, Chennubhotla S. ; Kasturi, Rangachar
Author_Institution :
Dept. of Electr. & Comput. Eng., Pennsylvania State Univ., University Park, PA, USA
Abstract :
The authors investigate a way of improving Hough transform performance using the spatial relations that exist between model features. Clusters of scene features possibly belonging to a model are grouped by a series of one-dimensional Hough transforms. The results presented illustrate the effectiveness of the methods
Keywords :
computer vision; computerised pattern recognition; transforms; object recognition; one-dimensional Hough transforms; pose clustering; scene features; spatial relations; Application software; Computer vision; Data engineering; Filtering; Layout; Libraries; Noise shaping; Object recognition; Shape; Smoothing methods;
Conference_Titel :
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-8186-2148-6
DOI :
10.1109/CVPR.1991.139654
