There is a growing demand for image processing in a wide range of applications such as
photography, robotics, television, remote sensing, industrial inspection, and medical …

Superpixel segmentation is the oversegmentation of an image into a connected set of
homogeneous regions. Depending on the algorithm, superpixels have specific properties …

A wide variety of computer vision applications rely on superpixel or supervoxel algorithms as
a preprocessing step. This underlines the overall importance that these approaches have …

Smart environments provide natural and intuitive human-computer interaction to support
people in their daily lives. For this functionality, the computers must be able to perceive …

In this thesis, we address a number of challenges in cluster analysis. We begin by
investigating one of the oldest and most challenging problems: determining the number of …

Various computer vision algorithms make use of superpixels in order to segment images.
Usually superpixels oversegment images and thereby are merged or erased by evaluating …