Abstract. We investigate the suitability of different local feature detectors for the task of automatic image orientation under different scene texturings. Building on an existin...
We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley Segment...
Plus BROWSE SEARCH IEEE XPLORE GUIDE SUPPORT View TOC Enhanced visual evaluation of feature extractors for image mining Rodrigues, J.F., Jr. Traina, A.J.M. Traina, C., Jr. Comput. ...
Image registration algorithms provide a displacement field between two images. We consider the problem of estimating accuracy of the calculated displacement field from the input i...
Comparative evaluation of visualization and experiment results is a critical step in computational steering. In this paper, we present a study of image comparison metrics for quan...