A Comparative Study of BRISK, ORB and DAISY Features for Breast Cancer Classification

Ghada Ouddai, Ines Hamdi, Henda Ben Ghezala

2023

Abstract

Medical data analysis is one of the most emergent fields over the past decades. In Digital histopathology, images are analysed, mainly, to detect disease or tumors and identify their types and grade. One of the most used practices in this field is the feature extraction. In this paper, we propose the application of BRISK, ORB and BRISK/DAISY on RGB histological images. The purpose of this work is to recognise the breast tumor type (benign or malignant). These features extractors are combined with BoF by kmeans and SVM. A limited amount of images is used during the training of the system. Out of the three methods, Color-BRISK/BoF/SVM solution gave the best accuracy value (72.5%) while Color-ORB/BoF/SVM was the fastest.

Paper Citation

in Harvard Style

Ouddai G., Hamdi I. and Ben Ghezala H. (2023). A Comparative Study of BRISK, ORB and DAISY Features for Breast Cancer Classification. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 964-970. DOI: 10.5220/0011902200003411

in Bibtex Style

@conference{icpram23,
author={Ghada Ouddai and Ines Hamdi and Henda Ben Ghezala},
title={A Comparative Study of BRISK, ORB and DAISY Features for Breast Cancer Classification},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={964-970},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011902200003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Comparative Study of BRISK, ORB and DAISY Features for Breast Cancer Classification
SN - 978-989-758-626-2
AU - Ouddai G.
AU - Hamdi I.
AU - Ben Ghezala H.
PY - 2023
SP - 964
EP - 970
DO - 10.5220/0011902200003411