ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Performance Analysis of Color based Image Retrieval

Journal: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY (Vol.12, No. 4)

Publication Date:

Authors : ; ;

Page : 3373-3381

Keywords : Content-based image retrieval (CBIR); color histogram; color spaces; Euclidean distance; City block distance; precision; recall;

Source : Download Find it from : Google Scholarexternal

Abstract

Recently Content based image retrieval (CBIR) is an active research. This paper proposes a technique to retrieve images based on color feature and evaluate the retrieval system performance. In this retrieval system Euclidean distance and City block distance are used to measure similarity of images. This algorithm is tested by using Corel image database which is provided by James Wang.? The performance of retrieval system is measured in terms of its recall and precision.? The effectiveness of retrieval system is also measured based on Average Rank (AVRR) of all relevant retrieves images and Ideal Average Rank of relevant images (IAVRR). The experimental results show that city block has achieved higher retrieval performance than Euclidean distance.

Last modified: 2016-06-29 18:20:48