Rendering performance of consumer graphics hardware benefits from pre-processing geometric data into a form targeted to the underlying API and hardware. The various elements of ge...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
This paper presents a new approach for generation of superresolution stereoscopic and multi-view video from monocular video. Such multi-view video is used for instance with multi-...
This paper proposes a chaotic fingerprint images encryption approach. An image of a fingerprint is encrypted via a twodimensional (2D) chaotic sequence obtained from multi-scrol...
Three-dimensional (3D) registration is the process aligning the range data sets form different views in a common coordinate system. In order to generate a complete 3D model, we nee...
Sang-Hoon Kim, Yong Ho Hwang, Hyun-Ki Hong, Min-Hy...