Similarity measure learning for image retrieval using binary component discriminating function

Practical content-based image retrieval systems require efficient relevance feedback techniques. Researchers have proposed many relevance feedback methods using quadratic-form distance metric as similarity measure and learning similarity matrix from feedback samples by linear transform. Existing linear approaches do not deal with data distribution in real image database very well. In this paper, a novel approach using binary component discriminant function (BCDF) is proposed by generalizing the original quadratic-form distance metric. The BCDF approach leams similarity measure nonlinearly by scatter criterion and distance criterion and deals with data distribution of feedback samples from real image database reasonably well. Experiments on a large database of 13,897 heterogeneous images demonstrated a remarkable improvement of retrieval precision compared with linear approaches.