Clustering Image with KL Divergence Husty Serviana Husain a) Sapto Wahyu Indratno b)
a) School of Mathematics, Bandung Institute of Technology
Jalan Ganesha 10, Bandung 40132, Indonesia and Indonesia University of Education.
b) School of Mathematics, Bandung Institute of Technology
Jalan Ganesha 10, Bandung 40132
Abstract
Grouping divides a population or data point into several groups so that data points in the same group are more similar to other data points in the same group than those in other groups. In simple words, the goal is to separate groups of the exact nature and assign them into groups. In this paper, image clustering will be done using K-means but for the distance between the distribution functions of each image and looking for the minimum distance value from each distribution function, and grouping based on that value. This paper will determine two formulas, namely Kullback-Leibler divergence and Jensen-Shannon divergence, to compare accuracy. In comparison, the distribution function is based on pixel distribution
