Image Retrieval by Shape and Color Contents and Relevance Feedback

Abstract

In the current era of digital communication, the use of digital images has grown high for expressing, sharing and interpreting information. While working with the digital images it is quite often that one needs to search for a specific image for a particular situation based on the visual contents of the image. Image retrieval by contents is one of the modern ways for searching huge digital image repositories for specific images. With the growing usage of World Wide Web CBIR is now very commonly used on most of the websites, software and database systems. In past years much of the research has been conducted in this domain and many CBIR systems have been proposed, implemented and being used. Different CBIR systems have different approaches to find images based on their contents and thus they have different performance and accuracy measures. There are some really smart techniques proposed by researchers for efficient and robust content based image retrieval. In this research, the aim is to highlight the efforts of researchers who conducted some brilliant work, based on this knowledge I will propose new combinational techniques for Content Based Image Retrieval focusing high performance and improved relevance and will provide proof of concept for intelligent content based image retrieval.