High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
We discuss problems in developing policies for ground truthing document images for pixel-accurate segmentation. First, we describe ground truthing policies that apply to four diff...
Abstract. This paper describes methods of extracting region boundaries from the frames of an image sequence by combining information from spatial or temporal cooccurrence matrices ...
Abstract. Training and evaluation of techniques for handwriting recognition and retrieval is a challenge given that it is difficult to create large ground-truthed datasets. This is...
A new method is presented to quantify malignant changes in histological sections of prostate tissue immunohistochemically stained for prostate-specific antigen (PSA) by means of im...
Ulf-Dietrich Braumann, Jens-Peer Kuska, Markus L&o...