Relevance feedback: a power tool for interactive content-based image retrieval

TLDR

Content‑based image retrieval has attracted extensive research, yet its effectiveness remains limited by the mismatch between high‑level concepts and low‑level features and by the subjectivity of human visual perception. This study introduces a relevance‑feedback interactive retrieval method that explicitly addresses the concept–feature gap and perceptual subjectivity. The method updates feature weights in real time according to user feedback, thereby aligning the system’s representation with the user’s high‑level query and perceptual preferences. Experiments on over 70,000 images demonstrate that the approach markedly reduces query‑composition effort and more accurately captures users’ information needs.

Abstract

Content-based image retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research efforts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Specifically, these efforts have relatively ignored two distinct characteristics of CBIR systems: (1) the gap between high-level concepts and low-level features, and (2) the subjectivity of human perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which effectively takes into account the above two characteristics in CBIR. During the retrieval process, the user's high-level query and perception subjectivity are captured by dynamically updated weights based on the user's feedback. The experimental results over more than 70000 images show that the proposed approach greatly reduces the user's effort of composing a query, and captures the user's information need more precisely.