Uncertainty always exists as an unavoidable factor when developing context-aware applications for pervasive computing environments [1][2][3][4]. In this paper, we propose a unifie...
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingl...
Example-based learning of codes that statistically encode general image classes is of vital importance for computational vision. Recently, non-negative matrix factorization (NMF) ...
We describe an extension of B-splines to surfacesof arbitrary topology, including arbitrary boundaries. The technique inherits many of the properties of B-splines: local control, ...
Converting point samples and/or triangular meshes to a more compact spline representation for arbitrarily topology is both desirable and necessary for computer vision and computer ...