E3S Web Conf.
Volume 75, 2019Regional Problems of Earth Remote Sensing (RPERS 2018)
|Number of page(s)||6|
|Section||Methods and Algorithms for Image Processing|
|Published online||14 January 2019|
Semi-supervised learning through hierarchical clustering for interactive aerospace image analysis
Institute of Computational Technologies of Siberian Branch of the Russian Academy of Sciences, 630090, Academician M.A. Lavrentiev avenue, 6, Novosibirsk, Russia
* Corresponding author: RylovS@mail.ru
A new semi-supervised classification algorithm based on the non-parametric clustering algorithm HCA is proposed. The algorithm obtains hierarchical segmentation result where additional classes that are not represented in the training samples can be found. High performance of the algorithm allows using it in interactive mode. Experimental studies confirm that the proposed algorithm provides aerospace image classification in conditions of limited number of training samples.
© The Authors, published by EDP Sciences, 2018
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.