AN IMPROVED CONTENT BASED IMAGE RETRIEVAL APPROACH USING LOCAL BINARY PATTERN (LBP)

The increased necessity of content based image retrieval (CBIR) technique can be found in a variety of different domains such as Data Mining (DM), Education, Medical Imaging (MI), Weather forecasting Crime Prevention, , Remote Sensing (RS) etc. An image retrieval system permits us to browse, search & retrieve the images. In past because of very huge image collections the manual annotation approach was more tedious. In order to conquer these difficulties content based image retrieval (CBIR) was introduced. This paper presents the content based image retrieval (CBIR), using local binary pattern (LBP). The local binary pattern encodes the relationship between the referenced pixel & its surrounding neighbors by computing the GLD (gray-level difference). The objective of the proposed methodology is to retrieve the best images from the stored database that resemble the query image with an optimized way.