Title :
Distortion-invariant object representation and discrimination using an FST neural net
Author :
Casasent, David ; Sipe, Michael ; Talukder, Ashit
Author_Institution :
Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
A feature space trajectory (FST) neural net is used to represent distorted versions of an object. Its use in determining the class and pose of an object is addressed with attention to: which aspect views and how many are needed to represent an object, which viewpoint gives the best pose animate and the best classification confidence. New eigen features are also advanced to provide improved results
Keywords :
CAD; active vision; image classification; image representation; neural nets; robot vision; aspect views; classification confidence; distortion-invariant object discrimination; distortion-invariant object representation; eigen features; feature space trajectory neural net; Adaptive algorithm; Infrared sensors; Inspection; Neural networks; Neurons; Robot sensing systems; Robot vision systems; Robotic assembly; Testing; Vehicles;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687161
