Evaluating the attributes of remote sensing image pixels for fast k-means clustering

Abstract

Clustering process is an important stage for many data mining applications. In this process, data elementsare grouped according to their similarities. One of the most known clustering algorithms is the k-means algorithm.The algorithm initially requires the number of clusters as a parameter and runs iteratively. Many remote sensing imageprocessing applications usually need the clustering stage like many image processing applications. Remote sensingimages provide more information about the environments with the development of the multispectral sensor and lasertechnologies. In the dataset used in this paper, the infrared (IR) and the digital surface maps (DSM) are also suppliedbesides the red (R), the green (G), and the blue (B) color values of the pixels. However, remote sensing images come withvery large sizes (6000 × 6000 pixels for each image in the dataset used). Clustering these large-size images using theirmultiattributes consumes too much time if it is used directly. In the literature, some studies are available to acceleratethe k-means algorithm. One of them is the normalized distance value (NDV)-based fast k-means algorithm that benefitsfrom the speed of the histogram-based approach and uses the multiattributes of the pixels. In this paper, we evaluatedthe effects of these attributes on the correctness of the clustering process with different color space transformations anddistance measurements. We give the success results as peak signal-to-noise ratio and structural similarity index valuesusing two different types of reference data (the source images and the ground-truth images) separately. Finally, we givethe results based on accuracy measurement for evaluating both the success of the clustering outputs and the reliabilityof the NDV-based measurement methods presented in this paper.