Share Email Print
cover

Proceedings Paper

Detection of distorted frames in retinal video-sequences via machine learning
Author(s): Radim Kolar; Ivana Liberdova; Jan Odstrcilik; Michal Hracho; Ralf P. Tornow
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes detection of distorted frames in retinal sequences based on set of global features extracted from each frame. The feature vector is consequently used in classification step, in which three types of classifiers are tested. The best classification accuracy 96% has been achieved with support vector machine approach.

Paper Details

Date Published: 28 July 2017
PDF: 4 pages
Proc. SPIE 10413, Novel Biophotonics Techniques and Applications IV, 104130A (28 July 2017); doi: 10.1117/12.2284172
Show Author Affiliations
Radim Kolar, Brno Univ. of Technology (Czech Republic)
Ivana Liberdova, Brno Univ. of Technology (Czech Republic)
Jan Odstrcilik, Brno Univ. of Technology (Czech Republic)
Michal Hracho, Brno Univ. of Technology (Czech Republic)
Ralf P. Tornow, Friedrich-Alexander-Univ. Erlangen–Nürnberg (Germany)


Published in SPIE Proceedings Vol. 10413:
Novel Biophotonics Techniques and Applications IV
Arjen Amelink, Editor(s)

© SPIE. Terms of Use
Back to Top