| H. Stokman and T. Gevers, "Detection and Classification of Hyper-Spectral Edges," Proc. loth British Machine Vision Conf., pp. 643-651, 1999. |
....from multiple images of the same scene, captured with different spectral narrow band filters. The assumptions underlying their approach require a smoothly varying illumination. Their method is able to accurately estimate surface reflectance independent of the scene geometry. Stokman and Gevers [6] propose a method for edge classification from spectral images. Their method aims in detecting edges and assigning one of the types; shadow or geometry, highlight, or a material edge. Under the assumption of spectral narrow band filters, and for a known illumination spectrum, they prove their ....
H. Stokman and T. Gevers, "Detection and Classification of Hyper-Spectral Edges," Proc. loth British Machine Vision Conf., pp. 643-651, 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC