CBIR using Relevance Feedback Retrieval System

Image retrieval is an important topic in the field of pattern recognition and artificial intelligence. Generally speaking, there are three categories of image retrieval methods: text-based, content-based and semantic-based. In CBIR, images are indexed by their visual content, such as color, texture, shapes. A new image feature detector and descriptor, namely the micro-structure descriptor (MSD)[1] is discussed to describe image features via micro-structures. The micro-structure are defined based on the edge orientation similarity, and the MSD is built based on the underlying colors in micro-structures with similar edge orientation. Content-based image retrieval (CBIR) is the mainstay of image retrieval systems. To be more profitable relevance feedback techniques are incorporated into CBIR such that more precise results can be obtained by taking user‟s feedbacks into account. In this paper, novel framework method called Relevance Feedback is used to achieve high efficiency and effectiveness of CBIR in coping with the large-scale image data. In terms of efficiency, iteration of feedback are reduced substantially by using the navigation patterns discovered from the user query log. In terms of effectiveness, our proposed work makes use of the discovered navigation patterns using three kinds of query refinement strategies, Query Point Movement (QPM), Query Reweighting (QR), and Query Expansion (QEX), to converge the search space toward the user‟s intention effectively. By using this method, high quality of image retrieval on RF can be achieved in a small number of feedbacks.