In this paper, we tackle the problem of localizing graphical symbols on complex technical document images by using an original approach to solve the subgraph isomorphism problem. ...
In this paper, the geometry of a general class of projections from ??? to ?! is examined, as a generalization of classic multiple view geometry in computer vision. It is shown that...
We present an algorithm that extracts the largest shape within a specificclass, starting from a set of image edgels. The algorithm inherits the Best-First Segmentation approach [jp...
This paper introduces an unsupervised color segmentation
method. The underlying idea is to segment the input
image several times, each time focussing on a different
salient part...
Michael Donoser, Martin Urschler, Martin Hirzer an...
This paper proposes an automatic foreground segmentation system based on Gaussian mixture models and dynamic graph cut algorithm. An adaptive perpixel background model is develope...