论文信息 - Distortion-invariant object representation and discrimination using an FST neural net

Distortion-invariant object representation and discrimination using an FST neural net

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.

David Casasent | Ashit Talukder | Michael A. Sipe

[1] Thierry Denoeux,et al. Initializing back propagation networks with prototypes , 1993, Neural Networks.

[2] David P. Casasent,et al. Classifier and shift-invariant automatic target recognition neural networks , 1995, Neural Networks.

[3] David Casasent,et al. GENERAL METHODOLOGY FOR SIMULTANEOUS REPRESENTATION AND DISCRIMINATION OF MULTIPLE OBJECT CLASSES , 1998 .

[4] Keinosuke Fukunaga,et al. Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

[5] Rajesh Shenoy,et al. Feature space trajectory for distorted-object classification and pose estimation in synthetic aperture radar , 1997 .

[6] David Haussler,et al. What Size Net Gives Valid Generalization? , 1989, Neural Computation.