Visual clustering method using genetic algorithm and image manipulation

Abstract

Clustering method has been applied in many fields, including data mining, machine learning, information retrieval, and image analysis. In this paper, we propose a visual clustering method based on the genetic algorithm (GA) and image manipulation. The proposed method automatically determines the number of clusters in a binary image without using distance measures. There are three processes of the proposed method, i.e., creating the object table, mapping the object table into a binary image, and clustering objects in the binary image by using the GA and image manipulation. The effectiveness of the proposed method is tested on both synthetic data sets and a real data set. The experimental results show that the proposed method can effectively construct the clusters in both synthetic and real data sets. © 2011 IEEE.