While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
On a large group picture, having all people open their eyes can turn out to be a difficult task for photographers. Therefore, in this paper, we describe an original method to auto...
Jean Charles Bazin, Dang-Quang Pham, Inso Kweon, K...
Abstract. This paper presents the hardware and software design principles of the medium size RoboCup Team CoPS which are developed by the image understanding group at the Institute...
Reinhard Lafrenz, Michael Becht, Thorsten Buchheim...
In this paper, we propose a new method for face recognition under varying illumination conditions using a single input image. Our method is based on a statistical shape-from-shadin...
Multimedia content presents special challenges for the search engines, and could benefit from semantic annotation of images. Unfortunately, manual labeling is too tedious and tim...
Chien-Ju Ho, Tsung-Hsiang Chang, Jane Yung-jen Hsu