Accession Number : ADD016539

Title :   Neural Network for Detection and Correction of Local Boundary Misalignments Between Images.

Descriptive Note : Patent, Filed 28 Jul 92, patented 27 Sep 94,

Corporate Author : DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s) : Rogers, George W ; Solka, Jeffrey L ; Vermillion, Donald ; Priebe, Carey E ; Poston, Wendy L

Report Date : 27 Sep 1994

Pagination or Media Count : 10

Abstract : A network is provided for the detection and correction of local boundary misalignments in a two-dimensional pixel space between a reference and transformed image. An input layer has input layer sections, each of which contains a plurality of input nodes associated with a cell. The cell is centered on a pixel and divided along a straightline orientation into first and second cell sections. Each of the input nodes outputs a digital signal indicative of the presence or absence of a contrast gradient as measured by the two cell sections. A second layer has a plurality of second layer sections, each of which is associated with one of the input layer sections and contains a plurality of second layer nodes. Each second layer node is responsive to a combination of input nodes to indicate the presence or absence of a boundary misalignment between the reference and transformed images. Presence of a contrast gradient at the combination of nodes defines a local boundary misalignment.

Descriptors :   *MISALIGNMENT, *PIXELS, *COMPUTER NETWORKS, *NEURAL NETS, BOUNDARIES, CELLS, CONTRAST, CORRECTIONS, DETECTION, GRADIENTS, IMAGES, INPUT, LAYERS, NODES, OUTPUT, SIGNALS, TWO DIMENSIONAL, PATENTS

Subject Categories : Computer Hardware
      Computer Programming and Software

Distribution Statement : APPROVED FOR PUBLIC RELEASE