Land-cover supervised classification using user-oriented feature database

In order to utilize remote sensed images effectively, a lot of image classification methods have been suggested for many years. But the accuracy of traditional methods based on pixel-based classification is not high in general. In the case of supervised classification, users should select training data sets within the image that are representative of the land-cover classes of interest. Users feel inconvenience extracting training data sets for image classification. In this paper, object oriented classification of Landsat images using a feature database is studied in consideration of user´s convenience and classification accuracy. Object oriented image classification, currently a new classification concept, allows the integration of a spectral value, shape and texture and creates image objects. According to classification classes, objects statistics such as mean value, standard deviation and tasseled cap transformation component were constructed as a feature database. Seven classes (rural, forest, grass, agriculture, wetland, barren, water) were constructed in this study, and these will be served in a network to users for image classification training data sets. The proposed method has higher classification accuracy than that of traditional pixel-based supervised classification and gives a convenient environment to users.