Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
We introduce a novel framework for automatic detection of repeated patterns in real images. The novelty of our work is to formulate the extraction of an underlying deformed lattice...
In practice, understanding the spatial relationships between the surfaces of an object, can significantly improve the performance of object recognition systems. In this paper we p...
The recognition of dynamic scenes using 3D shapes could provide useful approaches for various applications. However, the conventional 3D-shape sensing systems dedicated for such s...
This paper presents and compares 3 methods for the statistical localization of partially occulted landmarks. In many real applications, some information is visible in images and s...
Barbara Romaniuk, Michel Desvignes, Marinette Reve...