CBIR using Relevance Feedback: Comparative analysis and major challenges

Abstract

Nowadays, Content-Based Image Retrieval (CBIR) is the mainstay of image retrieval systems. To understand the query semantics and users' expectations so as to communicate faithful results in terms of accuracy, Relevance Feedback (RF) was incorporated to CBIR systems. By allowing the user to assess iteratively the answers as relevant/irrelevant or even giving him/her the opportunity to specify a degree of relevance (user's feedbacks), the system creates a new query that better captures the user's needs, hence raising the opportunity to get more relevant image results. In this paper, we have focused on CBIR and basic concepts pertaining to it, as well as Relevance Feedback and its various mechanisms. An important contribution in this work is a comparative analysis of CBIR systems using reference feedback: major models and approaches are discussed in detail from early heuristic methods to recently optimal learning algorithms, with more emphasize on their advantages and weaknesses.