HIERARCHICAL INDEXING FOR FASTER RETRIEVAL BASED ON FULL AUTOMATIC ALGORITHM

In this paper, we aim to take advantage of texture properties of images to improve the performance of the image indexing and retrieval algorithm. Beside that a framework for segmentation of the image which results in categorizing and identifying the object in image is presented. Image retrieval based on region is one of the most promising and active research directions in recent years. In this study, the combination of the texture features and regioing method provide an efficient feature set for image retrieval. Experimental results exhibit that the proposed method yield higher retrieval accuracy than some conventional methods even though its feature vector length and feature generating time of query image is less than those of other approaches.