A new approach for image retrieval with integrated Euclidean distance and rotational correlation

While existing image retrieval techniques primarily use distance to judge whether two images are similar or not, we propose to introduce an additional rotational correlation test to formulate a combined content similarity detection. We show that, with the same content based image retrieval algorithm, adding rotational correlation to the existing operational process can improve the performance of content based image retrieval significantly, providing a possible solution to the problem that minimum distance in low-level features does not necessarily lead to a content match.