For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Recognition of Elevation Symbols and Reconstruction of 3D Surface from Contours by Parallel Method
Kazuhiko YAMAMOTO Hiromitsu YAMADA Sigeru MURAKI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1994/07/25
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Document Analysis and Recognition)
erosion, dilatation, parallel operation, symbol recognition, regularization, topographic map,
Full Text: PDF(553.6KB)>>
In this paper, symbols and numerals in topographic maps are recognized by the multi-angled parallelism (MAP) matching method, and small dots and lines are extracted by the MAP operation method. These results are then combined to determine the value, position, and attributes of elevation marks. Also, we reconstruct three dimensional surfaces described by contours, which is difficult even for humans since the elevation symbols are sparse. In reconstruction of the surface, we define an energy function that enfores three constraints: smoothness, fit, and contour. This energy function is minimized by solving a large linear system of simultaneous equations. We describe experiments on 25,000:1 scale topographic maps of the Tsukuba area.