Content Based Image Retrieval Using Clustering
This paper presents novel techniques for image retrieval using the clustering features extracted from images based on Row Mean Clustering, Column Mean clustering, Row Mean DCT Clustering, Column Mean DCT Clustering, Row Mean Wavelet Clustering and Column Mean Wavelet Clustering. The proposed techniques are compared with well known traditional technique such as Hierarchical Clustering. Hierarchical clustering starts by calculating the Euclidean distance measure for all patterns in data set, which is not required to calculate in proposed techniques. Hence number of clusters used for comparison of proposed techniques is less as compared to existing technique (Hierarchical Clustering). All the CBIR techniques are implemented on a database having 665 images spread across 31 classes.