ct 8 For a specific set of features chosen for representing images, the performance of a content-based image retrieval (CBIR) system 9 depends critically on the similarity or dissimilarity measure used. Instead of manually choosing a distance function in advance, a more 10 promising approach is to learn a good distance function from data automatically. In this paper, we propose a kernel approach to 11 improve the retrieval performance of CBIR systems by learning a distance metric based on pairwise constraints between images as super12 visory information. Unlike most existing metric learning methods which learn a Mahalanobis metric corresponding to performing linear 13 transformation in the original image space, we define the transformation in the kernel-induced feature space which is nonlinearly related 14 to the image space. Experiments performed on two real-world image databases show that our method not only improves the retrieval 15 performance of Euclidean distance without distan...