DocumentCode :
3401760
Title :
Adaptive neural network for pattern recognition of 2-D image under affine transformation
Author :
Chen, Yiping ; Han, Jia-Yuan
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
fYear :
1991
fDate :
14-17 May 1991
Firstpage :
328
Abstract :
Presents a method for recognition of a 2-D image under affine transformation, which can be used as the preprocessing unit in an adaptive neural network. The affine transformation is decomposed into six basic transformations: x-direction and y-direction translations, rotation, x-direction and y-direction expansions (or compressions), and x-direction shear. In order to recognize a 2-D image under affine transformation, the authors introduce the normalized form of an image and design the normalizer by which one can transform an arbitrary input image to its normalized form. The recognition of the images can be done by comparing their normalized forms with a neural network identifier. Some experimental results are reported
Keywords :
image recognition; neural nets; 2D image recognition; adaptive neural network; affine transformation; neural network identifier; normalized form; pattern recognition; preprocessing unit; x-direction expansions; x-direction shear; x-direction translations; y-direction expansions; y-direction translations; Adaptive systems; Cameras; Eyes; Humans; Image recognition; Neural networks; Object recognition; Parallel processing; Pattern recognition; Shape measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1991., Proceedings of the 34th Midwest Symposium on
Conference_Location :
Monterey, CA
Print_ISBN :
0-7803-0620-1
Type :
conf
DOI :
10.1109/MWSCAS.1991.252164
Filename :
252164
Link To Document :
بازگشت