With the advancement of computer graphics in the recent years, an increasing number of pictures, video and 3D content is generated by synthesis processing rather than acquired wit...
We present a vision-based method that assists human
navigation within unfamiliar environments. Our main contribution
is a novel algorithm that learns the correlation between
use...
In this paper, we present a novel method for processing double-sided historic handwritten documents using wavelets. The method is specially designed to remove the interfering stro...
We propose a variational multigrid method for fast 3D interpretation of image sequences, in which a dense depth map and 3D motion are directly recovered from spatiotemporal change...
We present a document-specific OCR system and apply it to a corpus of faxed business letters. Unsupervised classification of the segmented character bitmaps on each page, using a ...