Hyper-spectral image segmentation using Rényi entropy based multi-level thresholding aided with differential evolution

作者：

Highlights：

• Unsupervised classification of land cover study of hyper-spectral satellite images.

• A multi-level Rényi entropy based image thresholding scheme is presented.

• Multi-level thresholding is formulated as optimization problem and solved with DE.

• Composite kernel based classification approach using Support Vector Machine (SVM).

• Very competitive performance on popular hyper-spectral imagery like ROSIS and AVRIS.

摘要

•Unsupervised classification of land cover study of hyper-spectral satellite images.•A multi-level Rényi entropy based image thresholding scheme is presented.•Multi-level thresholding is formulated as optimization problem and solved with DE.•Composite kernel based classification approach using Support Vector Machine (SVM).•Very competitive performance on popular hyper-spectral imagery like ROSIS and AVRIS.

论文关键词：Differential Evolution (DE),Hyper-spectral image,Multi-level image segmentation,Rényi entropy,Multiple learning kernel,Support Vector Machine (SVM)

论文评审过程：Received 8 September 2015, Revised 4 November 2015, Accepted 15 November 2015, Available online 31 December 2015, Version of Record 16 January 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.11.016