Relevance feedback is an important mechanism for narrowing the semantic gap in content-based image retrieval and the process involves the user labeling positive and negative images...
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
The approach proposed in this paper retrieves contours from transrectal ultrasound (TRUS) prostate images. The input images are sparsely annotated by radiologists for the purpose ...
Geoffroy Rivet Sabourin, Alexandra Branzan Albu, D...
—To construct 3D virtual scenes from two-dimensional images with depth information, image warping techniques could be used. In this paper, a novel approach of cylindrical depth i...
This paper introduces a new kind of mosaic, called Jigsaw Image Mosaic (JIM), where image tiles of arbitrary shape are used to compose the final picture. The generation of a Jigsa...