Geodesic
Probability distribution of transformed random variables with application to nonlinear features extraction
Kybernetika, Tome 34 (1998) no. 4, pp. 473-478 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

A method for estimation of probability distribution of transformed random variables is presented. The proposed approach admits an approximation of the transformation of the random variables. The approximate probability density function (pdf) is corrected to obtain a resulting pdf which incorporates a prior knowledge of approximation errors. The corrected pdf is not contaminated by any uncontrollable approximation. The method is applied to pattern recognition. It is shown that class conditional pdf of features can be easily computed even when the feature extraction was performed with nonlinear mapping of an input pattern.
A method for estimation of probability distribution of transformed random variables is presented. The proposed approach admits an approximation of the transformation of the random variables. The approximate probability density function (pdf) is corrected to obtain a resulting pdf which incorporates a prior knowledge of approximation errors. The corrected pdf is not contaminated by any uncontrollable approximation. The method is applied to pattern recognition. It is shown that class conditional pdf of features can be easily computed even when the feature extraction was performed with nonlinear mapping of an input pattern.
Classification : 62E15, 62F10, 62G05, 62H12, 65C60, 68T10
Keywords: probability density functions; estimation 
@article{KYB_1998_34_4_a19,
     author = {Soukup, Lubom{\'\i}r},
     title = {Probability distribution of transformed random variables with application to nonlinear features extraction},
     journal = {Kybernetika},
     pages = {473--478},
     year = {1998},
     volume = {34},
     number = {4},
     mrnumber = {1658929},
     zbl = {1274.62377},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_1998_34_4_a19/}
}
TY  - JOUR
AU  - Soukup, Lubomír
TI  - Probability distribution of transformed random variables with application to nonlinear features extraction
JO  - Kybernetika
PY  - 1998
SP  - 473
EP  - 478
VL  - 34
IS  - 4
UR  - http://geodesic.mathdoc.fr/item/KYB_1998_34_4_a19/
LA  - en
ID  - KYB_1998_34_4_a19
ER  - 
%0 Journal Article
%A Soukup, Lubomír
%T Probability distribution of transformed random variables with application to nonlinear features extraction
%J Kybernetika
%D 1998
%P 473-478
%V 34
%N 4
%U http://geodesic.mathdoc.fr/item/KYB_1998_34_4_a19/
%G en
%F KYB_1998_34_4_a19
Soukup, Lubomír. Probability distribution of transformed random variables with application to nonlinear features extraction. Kybernetika, Tome 34 (1998) no. 4, pp. 473-478. http://geodesic.mathdoc.fr/item/KYB_1998_34_4_a19/

[1] Kittler J.: Statistics and Images: 2. (K. V. Mardia, ed.), volume 2 of Advances in Applied Statistics, chapter Statistical pattern recognition in image analysis. Carfax Publishing Company, 1994

[2] Mařík R., Kittler J., Petrou M.: Error sensitivity assesment of vision algorithms based on direct error–propagation. In: Workshop on Performance Characteristics of Vision Algorithms (H. I. Christensen, W. Forstner, and C. B. Madsen, eds.), Cambridge 1996, pp. 45–58

[3] Soukup L.: Probability Distribution of an Approximated Function with Uncertain Argument. Research Report No. 1877, Institute of Information Theory and Automation, Prague 1996

[4] Soukup L.: Probability distribution of approximation. In: The 2nd European Workshop on Computer–Intensive Methods in Control and Signal Processing (L. Berec, J. Rojíček and M. Kárný, eds.), Institute of Information Theory and Automation, Prague 1996, pp. 141–144