17 March 2017 Random forest feature selection approach for image segmentation
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 1034117 (2017) https://doi.org/10.1117/12.2268694
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Abstract
In the field of image segmentation, discriminative models have shown promising performance. Generally, every such model begins with the extraction of numerous features from annotated images. Most authors create their discriminative model by using many features without using any selection criteria. A more reliable model can be built by using a framework that selects the important variables, from the point of view of the classification, and eliminates the unimportant once. In this article we present a framework for feature selection and data dimensionality reduction. The methodology is built around the random forest (RF) algorithm and its variable importance evaluation. In order to deal with datasets so large as to be practically unmanageable, we propose an algorithm based on RF that reduces the dimension of the database by eliminating irrelevant features. Furthermore, this framework is applied to optimize our discriminative model for brain tumor segmentation.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
László Lefkovits, Szidónia Lefkovits, Simina Emerich, Mircea Florin Vaida, "Random forest feature selection approach for image segmentation", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 1034117 (17 March 2017); doi: 10.1117/12.2268694; https://doi.org/10.1117/12.2268694
PROCEEDINGS
5 PAGES


SHARE
Back to Top