期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2012
卷号：9
期号：4
出版社：IJCSI Press
摘要：Data categorization is challenging job in a current scenario. The growth rate of a multimedia data are increase day to day in an internet technology. For the better retrieval and efficient searching of a data, a process required for grouping the data. However, data mining can find out helpful implicit information in large databases. To detect the implicit useful information from large databases various data mining techniques are use. Data clustering is an important data mining technique for grouping data sets into different clusters and each cluster having same properties of data. In this paper we have taken image data sets and firstly applying the density based clustering to grouped the images, density based clustering grouped the images according to the nearest feature sets but not grouped outliers, then we used an important super hyperplane classifier support vector machine (SVM) which classify the all outlier left from density based clustering. This method improves the efficiency of image grouping and gives better results.
