Improved techniques for Image Retrieval

Main Article Content

Priyanka Gupta
Mr. Umesh Kumar

Abstract

In this paper we are going to discuss content based image retrieval system considering multiple features as color, texture, shape and spatial
features to overcome the drawbacks of traditional text based image retrieval and previous content based image retrieval system which considered
only single or double features for matching similarity between images. Here we apply a sequence of algorithms for extracting color, texture, shape
and spatial features in CBIR for more accurate results, color feature vectors and clusters are formed using statistical color moments along with
hierarchical and K-means clustering technique and for texture feature extraction Gabor wavelets algorithm is implemented and on these features
extracted images shape features are extracted by implementing invariant moments then on this result images spatial feature is computed using the
concept of quad tree decomposition and now on retrieved images relevance feedback analysis is performed for automatic indexing of images for
future.


Keywords: CBIR, Clustering, Color moments, Gabor wavelet, invariant moments, quad tree decomposition

Downloads

Download data is not yet available.

Article Details

Section
Articles