Parallel processor for image segmentation
Johel Mitéran, Patrick Gorria, Michel Robert · 2002
We present the architecture of a parallel processor which is suitable for image segmentation. The classification of each pixel is completed using a geometric classification method by stress polytope training, which ensures a high decision speed (100 ns per pixels) and good performances. The decision operator has been integrated in the form of a full custom circuit developed in CMOS 1.2 /spl mu/m, and the area of silicon obtained is less than 30 mm/sup 2/.>