Performance Analysis of Clustering Algorithms for Character Recognition Using Weka Tool

Clustering is an unsupervised classification that is the partitioning of a data set in a set of meaningful subsets. Each object in dataset shares some common propertyoften proximity according to some defined distance measure. Among various types of clustering techniques, K-Means, Hierarchical and Make Density Based clustering are the most popular algorithms. Clustering Techniques are very useful in Character Recognition for automatically recognize the characters. In this paper we applied K-Means, Density Based and Hierarchical algorithms for clustering of Letter Image Recognition and Multi-Feature Digit data sets using WEKA machine learning tool. WEKA is a popular tool for machine learning which was written in java. The WEKA provides a collection of visualization tools and algorithms for data analysis and predictive modeling through a graphical user interface. Experimental results on Character Recognition data show that the k-means algorithms can make cluster in minimum time, and have good performance and the clustered accuracy is more than others two algorithms.