We combine information from a language model and character image pattern matching to iteratively reduce ambiguity in document images. Combining word shape information and lists of...
An algorithm is presented for 3-D reconstruction from optical flow observed by an uncalibrated camera. We show that by incorporating a statistical model of image noise, we can not...
d Abstract) Jieun Lee, Seung-Hyun Yoon, and Myunng-Soo Kim Seoul National University, KOREA We present a new approach to realistic hand modeling and deformation with real-time per...
— For a wide variety of sensor network environments, location information is unavailable or expensive to obtain. We propose a location-free, lightweight, distributed, and data-ce...
We introduce a new approach for mapping texture on volumetric iso-surfaces and parametric surfaces. Our approach maps 2D images on surfaces while maintaining continuity and preser...