Title :
Object recognition using neurocomputing and conformal computing geometry
Author :
López-Franco, Carlos ; Bayro-Corrochano, Eduardo
Author_Institution :
Dept. of Comput. Sci., GEOVIS Lab., Jalisco, Mexico
fDate :
31 July-4 Aug. 2005
Abstract :
In this paper we present an object recognition technique based on neural computing and projective invariants but now using an omnidirectional vision system and conformal geometric algebra. We also show how to recover the projective invariants from a catadioptric image, where the projective invariants do not hold. With these invariants we train a multilayer perceptron (MLP) neural network to recognize objects.
Keywords :
algebra; computational geometry; computer vision; multilayer perceptrons; object recognition; catadioptric image; conformal computing geometry; conformal geometric algebra; multilayer perceptron neural network; neural computing; object recognition; omnidirectional vision system; projective invariant; Algebra; Cameras; Computational geometry; Computer science; Computer vision; Laboratories; Machine vision; Multilayer perceptrons; Neural networks; Object recognition;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1556165
