Title :
A rotation, scaling and translation invariant pattern classification system
Author :
Yüceer, Cem ; Oflazer, Kemal
Author_Institution :
Dept. of Comput. Eng. & Inf. Sci., Bilkent Univ., Ankara, Turkey
fDate :
30 Aug-3 Sep 1992
Abstract :
Presents a hybrid pattern classification system which can classify patterns in a rotation, scaling, and translation invariant manner. The system is based on preprocessing the input image to map it into a rotation, scaling, and translation invariant canonical form, which is then classified by a multilayer feedforward neural net. Results from a number of classification problems are also presented in the paper
Keywords :
backpropagation; feedforward neural nets; image processing; backpropagation; canonical form; hybrid pattern classification system; multilayer feedforward neural net; rotation invariance; scaling invariance; translation invariance; Artificial neural networks; Backpropagation algorithms; Data preprocessing; Gravity; Information science; Neural networks; Neurons; Nonhomogeneous media; Pattern classification; Pattern recognition;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201808
