We present a novel approach for non-stationarity detection in natural images by exploiting the prior knowledge of the independent component structure of scene statistics. Our prop...
This paper explores a view-based approach to recognize free-form objects in range images. We are using a set of local features that are easy to calculate and robust to partial occ...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
Visualization users are increasingly in need of techniques for assessing quantitative uncertainty and error in the images produced. Statistical segmentation algorithms compute the...
Joe Michael Kniss, Robert L. Van Uitert Jr., Abrah...
We present a 3D brain MRI segmentation method in which a high resolution label image evolves under the influence of multiple constraints. The constraints are expressed in a versat...