This research investigates on satellite image categories classification using image processing and machine learning techniques. A satellite image is one of the important sources of the research-oriented platform which helps to monitor earth regularly. It provides information through multi-temporal images. It also ensures accurate data over a large geographical area in the world. The satellite image is independent of sunlight and atmospheric conditions so it is countered as the best source of an image detection device in remote sensing. The main objective of this research is to implement image analysis and classification techniques for extraction and finding the type of satellite images for clustering into groups. For this research 50, sample images were uses for the detection of satellite images. To characterize the type of satellite images, features collected as color-based, statistical features and texture features which achieved through wavelet transform technique and machine learning algorithms such as KNN classifier with 70% training and 30% testing data using a confusion matrix. This technique will ensure the category of satellite images through classification techniques. It ensures that db7 works well with 95% accuracy using the KNN classifier for the characterization of satellite images compare with other measures.