THIN NETS AND CREST LINES - APPLICATION TO SATELLITE DATA AND MEDICALIMAGES

In this paper, we describe a new approach for extracting thin nets in gray-level images. The key point of our approach is to model thin nets as crest lines of the image surface. Crest lines are lines where the magnitude maximum curvature is a local maximum in the corresponding pr incipal direction. We define these lines using first, second, and thir d derivatives of the image. The image derivatives are computed using r ecursive filters approximating the Gaussian filter and its derivatives . Using an adaptive scale factor, we apply this approach to the extrac tion of roads in satellite data, blood vessels in medical images, and actual crest lines in depth maps of human faces. (C) 1997 Academic Pre ss.