期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2014
卷号：5
期号：2
页码：109
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Hyperspectral image analysis has been used for many purposes in environmental monitoring, remotesensing, vegetation research and also for land cover classification. A hyperspectral image consists of manylayers in which each layer represents a specific wavelength. The layers stack on top of one another makinga cube-like image for entire spectrum. This work aims to classify the hyperspectral images and to producea thematic map accurately. Spatial information of hyperspectral images is collected by applyingmorphological profile and local binary pattern. Support vector machine is an efficient classificationalgorithm for classifying the hyperspectral images. Genetic algorithm is used to obtain the best featuresubjected for classification. Selected features are classified for obtaining the classes and to produce athematic map. Experiment is carried out with AVIRIS Indian Pines and ROSIS Pavia University. Proposedmethod produces accuracy as 93% for Indian Pines and 92% for Pavia University.
关键词：Morphological Profile; Local Binary Pattern; Hyperspectral Image; Genetic Algorithm; Support Vector;Machine
