Publication detail

Detection of distorted frames in retinal video-sequences via machine learning

KOLÁŘ, R. LABOUNKOVÁ, I. ODSTRČILÍK, J. HRACHO, M. TORNOW, R.

Original Title

Detection of distorted frames in retinal video-sequences via machine learning

Type

conference paper

Language

English

Original 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.

Keywords

retina; image processing; machine learning

Authors

KOLÁŘ, R.; LABOUNKOVÁ, I.; ODSTRČILÍK, J.; HRACHO, M.; TORNOW, R.

Released

29. 8. 2017

Publisher

SPIE-OSA

ISBN

9781510612846

Book

SPIE Proceedings (Optical Society of America)

Edition

Novel Biophotonics Techniques and Applications IV

Pages from

1

Pages to

4

Pages count

4

BibTex

@inproceedings{BUT138774,
  author="Radim {Kolář} and Ivana {Labounková} and Jan {Odstrčilík} and Michal {Hracho} and Ralf-Peter {Tornow}",
  title="Detection of distorted frames in retinal video-sequences via machine learning",
  booktitle="SPIE Proceedings (Optical Society of America)",
  year="2017",
  series="Novel Biophotonics Techniques and Applications IV",
  pages="1--4",
  publisher="SPIE-OSA",
  doi="10.1117/12.2284172",
  isbn="9781510612846"
}