A Semi-Supervised Deep Rule-Based Approach for Remote Sensing Scene Classication

Gu, Xiaowei and Angelov, Plamen Parvanov (2019) A Semi-Supervised Deep Rule-Based Approach for Remote Sensing Scene Classication. In: The 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference :. Springer, pp. 257-266. ISBN 9783030168407

[thumbnail of INNSBDDL34]
Preview
PDF (INNSBDDL34)
INNSBDDL34.pdf - Accepted Version

Download (805kB)

Abstract

This paper proposes a new approach that is based on the recently introduced semi-supervised deep rule-based classifier for remote sensing scene classification. The proposed approach employs a pre-trained deep convoluational neural network as the feature descriptor to extract high-level discriminative semantic features from the sub-regions of the remote sensing images. This approach is able to self-organize a set of prototype-based IF...THEN rules from few labeled training images through an efficient supervised initialization process, and continuously self-updates the rule base with the unlabeled images in an unsupervised, autonomous, transparent and human-interpretable manner. Highly accurate classification on the unlabeled images is performed at the end of the learning process. Numerical examples demonstrate that the proposed approach is a strong alternative to the state-of-the-art ones.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
130349
Deposited By:
Deposited On:
04 Jan 2019 16:00
Refereed?:
Yes
Published?:
Published
Last Modified:
09 Sep 2024 23:51