We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
The 2.1D sketch is a layered representation of occluding and occluded surfaces of the scene. Extracting the 2.1D sketch from a single image is a difficult and important problem ar...
In this paper a framework for the segmentation of cardiac MR image sequences using spatio-temporal appearance models is presented. The method splits the 4D space into 2 separate su...
This paper proposes a robust real-time, scalable and modular Field Programmable Gate Array (FPGA) based implementation of a spatiotemporal segmentation of video objects. The goal ...
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...