An Efficient Indexing for Content Based Image Retrieval Based on Number of Clusters Using Clustering Technique

Monika Jain, S. K. Singh, Kavita Saxena
2017 International Journal of Artificial Intelligence and Applications for Smart Devices  
Low-level visual features like color, shape, texture are being used for representing and retrieving images in many Content-Based Image Retrieval systems. Generally such methods suffer from the problems of high dimensionality leading to more computational time and inefficient indexing and retrieval performance. This paper focuses on a cluster based indexing technique for achieving efficient and effective retrieval performance. We present a simple index based on number of clusters that are
more » ... ed out of image based on color. A new cluster based similarity measure conforming to human perception is applied and shown to be effective. An unsupervised learning technique has been used to find number of clusters. Images are segmented to obtain homogeneous color regions that are dominant and images form an index stored in a hash structure. Each image is then indexed by a cluster index. In the fine matching stage, a reduced set of candidate images need to be computed for detailed similarity comparison. The experimental results show that proposed method leads to a fast retrieval with good accuracy.
doi:10.14257/ijaiasd.2017.5.1.01 fatcat:ooekqrtzmzeb7bculblaa4axuu