Robust and Effective Frame Work for Image Retrieval Scheme Using Shift Invariant Texture and Shape Features

Abstract

We aim to take advantage of both shape and texture properties of images to improve the performance of the image indexing
and retrieval algorithm. Beside that a framework for partitioning the image into non-overlapping tiles of different sizes which
results in higher retrieval efficiency is presented. In new approach, texture features are obtained with use of Shift Invariant dual-tree
complex wavelet transform (SIDT CWT) method. According to the new algorithm, image is divided into different regions, each
of them extracting features of Energy, standard deviation of each of the SIDT CWT which serve as local descriptors of texture.
Invariant momentums are then used to record the shape features. The combination of the texture features and shape features provide
a robust feature set for image retrieval. The most similar highest priority (MSHP) principle is provided for matching the images.
Experimental result show 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.