DocumentCode :
3174206
Title :
Assessments of neural network output codings for classification of multispectral images using Hamming distance measure
Author :
Chong, C.C. ; Jia, J.C.
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
Volume :
2
fYear :
1994
fDate :
9-13 Oct 1994
Firstpage :
526
Abstract :
The influences of different output codings on the performances of a back-propagation neural network for classification of multispectral images are investigated. The assessments of the output codings are based on the convergence ability, training and classification performances. Effects of the mapping permutation of output states to the information classes are discussed. Results obtained for all the possible permutations, of each coding scheme, are presented in terms of the statistical mean, variance, maximum and minimum of the performance features. Hamming distance measure is introduced as a tool to access the credibility of the coding schemes. Results obtained show that output coding schemes with equal Hamming distance between the output states have better generalization properties and performances obtained for different output mapping permutations are consistently high
Keywords :
image classification; Hamming distance measure; back-propagation neural network; convergence ability; generalization; mapping permutation; maximum; minimum; multispectral image classification; neural network output codings; statistical mean; variance; Electric variables measurement; Hamming distance; Image coding; Mirrors; Multispectral imaging; Neural networks; Temperature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
Type :
conf
DOI :
10.1109/ICPR.1994.577003
Filename :
577003
Link To Document :
بازگشت