Multi Query Image Retrieval System with Application to Mammogram Images

Abstract

Content Based Image Retrieval (CBIR) systems open new methods to efficiently manage large volumes of data. The proposed system accepts queries with single image and multiple images. The different queries are combined using logical AND. The features of the query image are compared with the features of the images stored in the database. The experimental result shows that the use of multiple queries has better retrieval performance than single image queries. This CBIR system is a general framework which can be used for different applications. In this study three kinds of texture features are used – Haralick texture features, Local Binary Patterns (LBP) and Haar wavelet features. The proposed system is tested with mammogram images.

Keywords: CBIR, CBMIR, image retrieval, feature extraction, breast cancer