This paper presents a novel approach for the multi-oriented text line extraction from historical handwritten Arabic documents. Because of the multi-orientation of lines and their ...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
This paper presents a linear algorithm for simultaneous computation of 3D points and camera positions from multiple perspective views based on having a reference plane visible in a...
— This paper introduces the establishment of PolyU Near-Infrared Face Database (PolyU-4 NIRFD) and presents a new coding scheme for face recognition. The PolyU-NIRFD contains ima...
Baochang Zhang, Lei Zhang 0006, David Zhang, Linli...
We present generative models dedicated to face recognition. Our models consider data extracted from color face images and use Bayesian Networks to model relationships between diffe...