An Efficient System for Color Image Retrieval Representing Semantic Information to Enhance Performance by Optimizing Feature Extraction

Abstract

Abstract Image retrieval is a well discussed field in digital image processing. Images can be sort out from a big collection and database of images on the basis of text, color and shape of objects in images. In CBIR systems, using combined features get many most similar and relevant images. In a typical CBIR system, the ocular content of the images from the large collection is extracted and displayed by a storehouse like m-dimensional feature vectors framed out from images. This vector of the images in the collection of images in database is named as a database of features. Most sought out systems represent images with color feature most related to user and shape feature to relate image to exact object from collection and test dataset. In this paper we present introduction, research work on color scheme with HSV colour space and its combination with shape using coiflet wavelet methods. States of art design of overall system is delineated with results evaluated for mean average precision and mean average recall for overall system.