Research on Modified SVM for Image classification in Remote Sensing
- 10.2991/amcce-17.2017.52How to use a DOI?
- Image classification, support vector machines, artificial neural network, kappa coefficient.
Image classification is based on the analysis in different time from the same area of two or more images, detect the feature in the region information changes over time. Remote sensing image classification has been widely used in such as the dynamic monitoring of forest resources monitoring, the change of land cover and use, agricultural resources survey, urban planning layout, environmental monitoring and analysis, assessment of natural disasters, geographic data update and military reconnaissance in the strategic objectives (such as roads, Bridges, airports) of dynamic monitoring and many other fields. SVM classifiers are most prominently used classifiers and they provide good accuracy. This research paper presents a modified SVM classifier by incorporating intelligence into the proposed system. Intelligence is provided by using an ANN architecture. The proposed SVM-ANN approach aims to reduce the impact of parameters in classification accuracy. In the training stage, the SVM is utilized to reduce the training samples for each of the available categories to their support vectors (SVs).The SVs from different categories are used as the training data of nearest neighbor classification algorithm in which the similarity measures or distance function is used to calculate the which class does the testing data belongs and which also reduce time consumption.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - CHuankai Zhang AU - Fangji Liang PY - 2017/03 DA - 2017/03 TI - Research on Modified SVM for Image classification in Remote Sensing BT - Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017) PB - Atlantis Press SP - 297 EP - 302 SN - 2352-5401 UR - https://doi.org/10.2991/amcce-17.2017.52 DO - 10.2991/amcce-17.2017.52 ID - Zhang2017/03 ER -