|
This article is cited in 18 scientific papers (total in 18 papers)
NUMERICAL METHODS AND DATA ANALYSIS
Informative feature selection based on the Zernike polynomial coefficients for various pathologies of the human eye cornea
P. A. Khorina, N. Yu. Ilyasovaab, R. A. Paringerab a Samara National Research University, Samara, Russia
b Image Processing Systems Institute îf RAS – Branch of the FSRC “Crystallography and Photonics” RAS, Samara, Russia
Abstract:
The study was devoted to the analysis of wavefront aberrations under changes of the cornea surface curvature in the human eye. The analysis was based on the representation of aberrations of the front and rear corneal surfaces as superposition of Zernike functions. Weight coefficients of the Zernike polynomials were the object of this study. The data under analysis were obtained in a number of clinical trials in the Branchevski’s eóå clinic. The most informative weight coefficients were analyzed from the point of view of classification of patients by particular diagnosis. A comparison of the classification results was carried out using thirty front and rear corneal features, as well as the most informative features. The features were ranked by the informativity criterion for solving a specific classification task. While doing analysis, the informativity was evaluated on the basis of values of a separability criterion. An additional estimation of informativeness was carried out by calculating the classification error by a K-means method. As a result of the analysis, basic Zernike functions that are most informative for particular eye pathologies were identified
Keywords:
aberrations of the cornea, Zernike functions, myopia of the human eye, classification, feature space, analysis of the informative features.
Received: 29.09.2017 Accepted: 26.11.2017
Citation:
P. A. Khorin, N. Yu. Ilyasova, R. A. Paringer, “Informative feature selection based on the Zernike polynomial coefficients for various pathologies of the human eye cornea”, Computer Optics, 42:1 (2018), 159–166
Linking options:
https://www.mathnet.ru/eng/co490 https://www.mathnet.ru/eng/co/v42/i1/p159
|
Statistics & downloads: |
Abstract page: | 265 | Full-text PDF : | 80 | References: | 29 |
|