Translator Disclaimer
6 April 1995 Learning to distinguish similar objects
Author Affiliations +
This paper describes how the similarities and differences among similar objects can be discovered during learning to facilitate recognition. The application domain is single views of flying model aircraft captured in silhouette by a CCD camera. The approach was motivated by human psychovisual and monkey neurophysiological data. The implementation uses neural net processing mechanisms to build a hierarchy that relates similar objects to superordinate classes, while simultaneously discovering the salient differences between objects within a class. Learning and recognition experiments both with and without the class similarity and difference learning show the effectiveness of the approach on this visual data. To test the approach, the hierarchical approach was compared to a non-hierarchical approach, and was found to improve the average percentage of correctly classified views from 77% to 84%.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Michael Seibert, Allen M. Waxman, and Alan N. Gove "Learning to distinguish similar objects", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995);


Semantically enabled image similarity search
Proceedings of SPIE (May 21 2015)
Behavioral model of visual perception and recognition
Proceedings of SPIE (September 08 1993)
Identification of vegetable diseases using neural network
Proceedings of SPIE (February 27 2007)
Attention trees and semantic paths
Proceedings of SPIE (February 12 2007)

Back to Top