Automatic Query Image Disambiguation for Content-Based Image Retrieval
This addresses the challenge of unclear user search objectives in image retrieval systems, offering an incremental improvement with minimal user interaction.
The paper tackles the problem of ambiguous query images in content-based image retrieval by proposing a technique that clusters the query neighborhood for user selection and integrates feedback to re-rank results, achieving a 23% relative improvement in average precision on the MIRFLICKR-25K dataset.
Query images presented to content-based image retrieval systems often have various different interpretations, making it difficult to identify the search objective pursued by the user. We propose a technique for overcoming this ambiguity, while keeping the amount of required user interaction at a minimum. To achieve this, the neighborhood of the query image is divided into coherent clusters from which the user may choose the relevant ones. A novel feedback integration technique is then employed to re-rank the entire database with regard to both the user feedback and the original query. We evaluate our approach on the publicly available MIRFLICKR-25K dataset, where it leads to a relative improvement of average precision by 23% over the baseline retrieval, which does not distinguish between different image senses.