In this paper, we develop a new approach for texture classification independent of affine transforms. Based on spectral representation of texture images under affine transform, an...
We propose textural features, which are invariant to illumination spectrum and extremely robust to illumination direction. They require only a single training image per texture an...
In this paper we report on an experience communicating two computer algebra systems, namely GAP (and more concretely, its HAP package to compute in Homological Algebra) and Kenzo ...
We show how a special decomposition of a set of two or three general projection matrices, called canonic enables us to build geometric descriptions for a system of cameras which a...
Features from the Scale Invariant Feature Transformation (SIFT) are widely used for matching between spatially or temporally displaced images. Recently a topology on the SIFT featu...