in this paper we propose a mathematical transform, based on several one-class support vector machines (SVM) models, to modify images at pixel level on the preprocessing stage in order to emphasize the difference of pixels between dissimilar regions. We show experimentally that the proposed transform does improve segmentation results of automatic thresholding algorithms such as Otsu, Mixture of Gaussians and k-means on biomedical images; specially in the presence of noise, clumped objects and difficult ROI identification.
Alioscha-Perez, M, Taboada, A & Sahli, H 2013, Mathematical Transform based on Regions Semantic for Improving Biomedical Images Segmentation. in R Llanusa & B Susana (eds), V Latin American Congress on Biomedical Engineering CLAIB 2011 May 16-21, 2011, Habana, Cuba: Sustainable Technologies for the Health of All. IFMBE Proceedings, vol. 33, Springer, Berlin, pp. 1058-1061, V Latin American Congress on Biomedical Engineering - CLAIB 2011, Habana, Cuba, 16/05/11.
Alioscha-Perez, M., Taboada, A., & Sahli, H. (2013). Mathematical Transform based on Regions Semantic for Improving Biomedical Images Segmentation. In R. Llanusa, & B. Susana (Eds.), V Latin American Congress on Biomedical Engineering CLAIB 2011 May 16-21, 2011, Habana, Cuba: Sustainable Technologies for the Health of All (pp. 1058-1061). (IFMBE Proceedings; Vol. 33). Springer.
@inproceedings{d4a010d69d844ccb8313d6b29974a296,
title = "Mathematical Transform based on Regions Semantic for Improving Biomedical Images Segmentation",
abstract = "in this paper we propose a mathematical transform, based on several one-class support vector machines (SVM) models, to modify images at pixel level on the preprocessing stage in order to emphasize the difference of pixels between dissimilar regions. We show experimentally that the proposed transform does improve segmentation results of automatic thresholding algorithms such as Otsu, Mixture of Gaussians and k-means on biomedical images; specially in the presence of noise, clumped objects and difficult ROI identification.",
keywords = "segmentation, cell images",
author = "Mitchel Alioscha-Perez and A. Taboada and Hichem Sahli",
note = "Ruiz Llanusa , B. Susana; V Latin American Congress on Biomedical Engineering - CLAIB 2011 ; Conference date: 16-05-2011 Through 21-05-2011",
year = "2013",
language = "English",
isbn = "978-3-642-21197-3",
series = "IFMBE Proceedings",
publisher = "Springer",
pages = "1058--1061",
editor = "Ruiz Llanusa and B. Susana",
booktitle = "V Latin American Congress on Biomedical Engineering CLAIB 2011 May 16-21, 2011, Habana, Cuba",
}