This article presents a genetic learning algorithm to derive discrete patterns that can be used for classification and retrieval of 3D motion capture data. Based on boolean motion ...
Bottom-up segmentation tends to rely on local features. Yet, many natural and man-made objects contain repeating elements. Such structural and more spread-out features are importa...
We present an energy based automatic image segmentation algorithm that uses a novel active contour scheme, called the stochastic active contour scheme (STACS). The algorithm overc...
Quantitative measurements of changes in evolving brain pathology, such as multiple sclerosis lesions and brain tumors, are important for clinicians to perform pertinent diagnoses a...
Automatic segmentation and analysis of ancient mosaic images can help archaeologists and experts build digital collections and automatically compare mosaics by means of image datab...