Memorial University DAI: Hierarchical fuzzy pattern matching for the regional comparison of land use maps

advanced search

Digital Archives Initiative
Memorial University - Electronic Theses and Dissertations 1

menu off

add document to favorites : add page to favorites : reference url

back to results : previous : next

Search this object:

0 hit(s) :: previous hit : next hit

View:

previous page : next page

Document Description

Title	Hierarchical fuzzy pattern matching for the regional comparison of land use maps
Author	Power, Conrad, 1965-
Description	Thesis (M.Sc.)--Memorial University of Newfoundland, 1998. Geography
Date	1998
Pagination	viii, 111 leaves : ill., maps
Subject	Land use--Maps; Land settlement patterns--Maps; Fuzzy algorithms; Pattern perception
Degree	M.Sc.
Degree Grantor	Memorial University of Newfoundland. Dept. of Geography
Discipline	Geography
Language	Eng
Notes	Bibliography: leaves 101-107.
Abstract	The evaluation of the spatial similarities between two raster maps is traditionally based on pixel-by-pixel comparison techniques. These procedures determine the number of ceils in agreement for each landuse category and express the overall agreement with a boolean global similarity value. The problem with a pixel-by-pixel comparison is that a small displacement in pixels will be registered as disagreement even though the land use patterns between the maps maybe essentially the same. The issues of unique polygons mapping and hierarchical fuzzy pattern matching, where the maps are compared on both a local and global level emerge as viable and robust alternatives. The local matchings determine the degree of containment of each unique polygon to its spatial counterparts on the original maps in terms of fuzzy areal intersections. Local agreement values for the unique polygons based on their polygon area containments are calculated from fuzzy logical Max-Min compositional algorithms. A global agreement value is derived by the fuzzy summation of the local matchings. The uses of these basic methods are discussed and further refinements and modeling possibilities are outlined.
Type	Text
Resource Type	Electronic thesis or dissertation
Format	Image/jpeg; Application/pdf
Source	Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries
Local Identifier	a1322326
Rights	The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.
Collection	Electronic Theses and Dissertations
Scanning Status	Completed
PDF File	(35.68 MB) -- http://collections.mun.ca/PDFs/theses/ConradPower.pdf
CONTENTdm file name	38145.cpd