Dendritic crystallogram images classification
- Authors: Paringer R.1, Kupriyanov A.1, Ilyasova N.1
-
Affiliations:
- Samara State Aerospace University, Image Processing Systems Institute of the Russian Academy of Sciences
- Issue: Vol 1, No 2 (2015)
- Pages: 135-138
- Section: Articles
- URL: https://jbpe.ssau.ru/index.php/JBPE/article/view/2470
- ID: 2470
Cite item
Full Text
Abstract
A computer classification system of dendritic crystallogram images is presented in this paper. To improve the quality of classification we use an algorithm for the informative features formation, using methods of discriminant analysis. The method for receiving an informativeness estimation was used. As basic features are seven geometric characteristic were calculated. The research confirming the efficiency of the formed features for classification of dendritic crystallogramms images was conducted by means of classification by support vector machine. Of these, was selected most informative basic five features and one new feature was formed. The error classification decreased from 0.081 to 0.061. The algorithm possesses a sufficient level of universality and may be applied to increase the informativeness of any feature set.
About the authors
Rustam Paringer
Samara State Aerospace University, Image Processing Systems Institute of the Russian Academy of Sciences
Author for correspondence.
Email: RusParinger@gmail.com
Russian Federation
Alexander Kupriyanov
Samara State Aerospace University, Image Processing Systems Institute of the Russian Academy of Sciences
Email: akupr@smr.ru
Russian Federation
Nataly Ilyasova
Samara State Aerospace University, Image Processing Systems Institute of the Russian Academy of Sciences
Email: ilyasova@smr.ru
Russian Federation