Accession Number : ADP000134

Title :   Linear Delineation,


Personal Author(s) : Fischler,Martin A.

Report Date : 1982

Pagination or Media Count : 9

Abstract : In this paper we address the most general version of the problem of achieving machine perception and tracing of 'line-like' structures appearing in an image; our goal is human level performance. We show that the problem can profitably be viewed as the process of finding skeletons in a gray scale image after observing (1) that line detection does not necessarily depend on gradient information, but rather is approachable from the standpoint of measuring total intensity variation, and (2) that smoothing the original image produces an approximate distance transform. We present an effective technique for extracting the delineating skeletons from an image, and show examples of this approach employing aerial, industrial, and radiographic imagery. (Author)

Descriptors :   *Image processing, Optical images, Edges, Contours, Gradients

Distribution Statement : APPROVED FOR PUBLIC RELEASE