Rotationally invariant pattern recognition by use of linear and nonlinear cascaded filters

We discuss the merits of using single-layer (linear and nonlinear) and multiple-layer (nonlinear) filters for rotationally invariant and noise-tolerant pattern recognition. The capability of each approach is considered with reference to a two-class, rotation-invariant, character recognition problem....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied Optics 2005-07, Vol.44 (20), p.4315-4322
Hauptverfasser:	Wu, Ning, Alcock, Robin D, Halliwell, Neil A, Coupland, Jeremy M
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial Intelligence Cluster Analysis Computer Simulation Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Linear Models Nonlinear Dynamics Numerical Analysis, Computer-Assisted Pattern Recognition, Automated - methods Reproducibility of Results Rotation Sensitivity and Specificity Signal Processing, Computer-Assisted
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!