Share Email Print
cover

Proceedings Paper

Semi-supervised classification of multi-spectral images based on density: selected samples
Author(s): X. Jing; S. Y. Chen; L. L. Fan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The precision of training samples has important influence on the accuracy of Supervised Classification of Remote Sensing Images. It is easy to omit the ground feature which covers a small amount by visual selection directly on the original image. This leads to a large number of wrong points and leakage points which influences the Classification Accuracy of Remote Sensing Images. Based on what was said above, we first use K-means clustering algorithm to initialize the samples in this paper. According to the clustering results, the training samples selected by visual labeling and density-based k-means algorithm participated in the SVM classification model. The results show that selecting training samples by the k-means algorithm based on density can reduce the influence of visual labeling on the subjective factors of training sample selection. Meanwhile,through the optimization of the radius weighting factor, we have found optimal combination of weighting factors and then the classification accuracy of remote sensing images can be increased from 81.70% to 88.89%.

Paper Details

Date Published: 21 July 2017
PDF: 6 pages
Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 1042030 (21 July 2017); doi: 10.1117/12.2281533
Show Author Affiliations
X. Jing, Xi'an Univ. of Science and Technology (China)
S. Y. Chen, Xi'an Univ. of Science and Technology (China)
L. L. Fan, Xi'an Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10420:
Ninth International Conference on Digital Image Processing (ICDIP 2017)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top