Abstract. Quality of segmentations obtained by 3D Active Appearance Models (AAMs) crucially depends on underlying training data. MRI heart data, however, often come noisy, incomple...
Many of the available image databases have keyword annotations associated with the images. In spite of the availability of good quality low-level visual features that reflect wel...
Abstract. In this paper, we target at face gender classification on consumer images in a multiethnic environment. The consumer images are much more challenging, since the faces cap...
We present an approach to recognizing faces with varying appearances which also considers the relative probability of occurrence for each appearance. We propose and demonstrate ex...
Nathan Mekuz, Christian Bauckhage, John K. Tsotsos
We study the problem of generating plausible interpretations
of a scene from a collection of line segments automatically
extracted from a single indoor image. We show that
we ca...