Abstract. Most current approaches to recognition aim to be scaleinvariant. However, the cues available for recognizing a 300 pixel tall object are qualitatively different from tho...
Numerous privacy models based on the k-anonymity property have been introduced in the last few years. While differing in their methods and quality of their results, they all focus...
Alina Campan, Traian Marius Truta, Nicholas Cooper
This paper presents an approach of fusing images from many video cameras or a moving video camera with external orientation data (e.g. GPS and INS data) into a few mosaiced images...
Object recognition has reached a level where we can identify a large number of previously seen and known objects. However, the more challenging and important task of categorizing ...
The recognition of script in historical documents requires suitable techniques in order to identify single words. Segmentation of lines and words is a challenging task because lin...