Comparing Machine Learning Techniques in a Hyperemia Grading Framework

L. S. Brea, N. Barreira, A. Mosquera, H. Pena-Verdeal, E. Yebra-Pimentel

2016

Abstract

Hyperemia is the occurrence of redness in a certain tissue. When it takes place on the bulbar conjunctiva, it can be an early symptom of different pathologies, hence, the importance of its quick evaluation. Experts grade hyperemia as a value in a continuous scale, according to the severity level. As it is a subjective and time consuming task, its automatisation is a priority for the optometrists. To this end, several image features are computed from a video frame that shows the patient’s eye. Then, these features are transformed to the grading scale by means of machine learning techniques. In previous works, we have analysed the performance of several regression algorithms. However, since the experts only use a finite number of values in each grading scale, in this paper we analyse how classifiers perform the task in comparison to regression methods. The results show that the classification techniques usually achieve a lower training error value, but the regression approaches classify correctly a larger number of samples.

Paper Citation

in Harvard Style

S. Brea L., Barreira N., Mosquera A., Pena-Verdeal H. and Yebra-Pimentel E. (2016). Comparing Machine Learning Techniques in a Hyperemia Grading Framework . In Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-172-4, pages 423-429. DOI: 10.5220/0005756004230429

in Bibtex Style

@conference{icaart16,
author={L. S. Brea and N. Barreira and A. Mosquera and H. Pena-Verdeal and E. Yebra-Pimentel},
title={Comparing Machine Learning Techniques in a Hyperemia Grading Framework},
booktitle={Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2016},
pages={423-429},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005756004230429},
isbn={978-989-758-172-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Comparing Machine Learning Techniques in a Hyperemia Grading Framework
SN - 978-989-758-172-4
AU - S. Brea L.
AU - Barreira N.
AU - Mosquera A.
AU - Pena-Verdeal H.
AU - Yebra-Pimentel E.
PY - 2016
SP - 423
EP - 429
DO - 10.5220/0005756004230429