返回Google圖書搜尋

Parameter Networks: Towards a Theory of Low-level Vision

出版	Department of Computer Science, University of Rochester, 1981
URL	http://books.google.com.hk/books?id=2pDtNwAACAAJ&hl=&source=gbs_api

註釋One of the most fundamental problems in vision is segmentation; the way in which parts of an image are perceived as a meaningful whole. Recent work has shown how to calculate images of physical parameters from raw intensity data. Such images are known as intrinsic images, and examples are images of velocity (optical flow), surface orientation, occluding contour, and disparity. The principal difficulty with intrinsic images is that each by itself is generally underconstrained; they can only be computed in parallel with each other and with the use of parameters obtained through segmentation. While intrinsic images are not segmented, they are distinctly easier to segment than the original intensity image. If parts of these images are organized in some way, this organization can be detected by a general Hough transform technique. Networks of feature parameters are appended to the intrinsic image organization. Then the intrinsic image points are mapped into these networks. This mapping will be many-to-one onto interesting parameter values. This basic relationship is extended into a general representation and control technique with the addition of three main ideas: abstraction levels; sequential search; and tight coupling. These ideas are a nucleus of a theory of low-level and intermediate-level vision. This theory explains segmentation in terms of highly parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction. (Author).