TY - JOUR AU - H. Thary Al-Ghrairi, Assad AU - H. Abed, Zahraa AU - H. Fadhil, Fatimah AU - K. Naser, Faten PY - 2018/10/14 Y2 - 2024/03/29 TI - Classification of Satellite Images Based on Color Features Using Remote Sensing JF - International Journal of Computer (IJC) JA - IJC VL - 31 IS - 1 SE - Articles DO - UR - https://www.ijcjournal.org/index.php/InternationalJournalOfComputer/article/view/1306 SP - 42-52 AB - <p>The aim of this paper is to classify satellite imagery using moment's features extraction with K-Means clustering algorithm in remote sensing. Clustering is the assignment of objects into groups called clusters so that objects from the same cluster are more similar to each other than objects from different clusters. In this research, the study area chosen is to cover the area of Baghdad city in Iraq taken by landsat 8. The proposed work consists of two phases: training and classification. The training phase aims to extract the moment features (mean, standard deviation, and skewness) for each block of the satellite imagery and store as dataset used in classification phase to compute the similarity measurement.  The experimental result of classification showed that the image contains five distinct classes (rivers, agriculture area, buildings with vegetation, buildings without vegetation, and bare lands). The classification result assessment was carried out by comparing the result with a reference classified image achieved by Iraqi Geological Surveying Corporation (GSC). It is observed that both the user accuracy and producers' accuracy and hence overall classification accuracy are enhanced with percent 92.12447%.<strong></strong></p> ER -