Title :
Object recognition using geometric hashing on the Connection Machine
Author :
Bourdon, Olivier ; Medioni, Gérard
Author_Institution :
Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
A parallel implementation of a system to recognize 2D objects under realistic scenarios (occlusion, rotation, translation, and perspective) is presented. A preprocessing phase and a recognition phase are used. Both phases have been implemented on the Connection Machine, achieving O(n-x) with nx processors (x⩽4) for preprocessing and O(n2) for recognition. The performance on the Connection Machine is compared with an implementation on a Sun 3/260
Keywords :
computational complexity; computerised pattern recognition; computerised picture processing; parallel processing; 2D object recognition; Connection Machine; geometric hashing; occlusion; parallel implementation; perspective; rotation; translation; Feature extraction; Intelligent robots; Intelligent systems; Layout; Machine intelligence; Object recognition; Parallel robots; Polynomials; Solid modeling; Sun;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.119438
