期刊名称：American Journal of Geographic Information System
印刷版ISSN：2163-1131
电子版ISSN：2163-114X
出版年度：2018
卷号：7
期号：5
页码：125-132
DOI：10.5923/j.ajgis.20180705.01
语种：English
出版社：Scientific & Academic Publishing Co.
摘要：Texture plays an important role in many machine vision tasks such as surface inspection, scene classification, and surface orientation and shape determination. For example, surface texture features are used in the inspection of semi-conductor wafers, gray-level distribution features of homogeneous textured regions are used in the classification of aerial imagery, and variations in texture patterns due to perspective projection are used to determine three dimensional shapes of objects. In this study, the effect of using auxiliary data in the classification results was investigated using the SVM classifier and specified training sample size, with generated Co-occurrence matrix attributes. Three investigations have been implemented: 1) using single attribute of each band. 2) Using the group attributes of each band. 3) Using the all attributes of bands and comparing the results with the case of RGB image only. The results showed that, the group of attributes of Blue band performed the best of the three bands. All classifiers are performing better using all attributes except for Neural Network. The variance attribute of the Blue and Green bands performed the best with the overall accuracy.
关键词：Textural Classification; SVM; GLCM; High resolution satellite imagery
