Article ID Journal Published Year Pages File Type
532542 Journal of Visual Communication and Image Representation 2012 6 Pages PDF
Abstract

It is known that after segmentation and morphological operations on topographic maps, gaps occur in contour lines. It is also well known that filling these gaps and reconstruction of contour lines with high accuracy is not an easy problem. In this paper, a nontrivial semi-automatic approach to solve this problem is proposed. The main idea of the proposed approach is based on local and geometric properties such as (1) parabolic and opposite directions, (2) the differences of y-ordinate of end points, (3) changing the directions of x-axis and y-ordinate to the nearest clockwise direction and (4) avoiding the use of the second end point of a small piece of any contour line in the same mask if its other end point is used. The proposed approach was implemented on the base of many topographic maps with different resolutions and complexity. The obtained results show that the proposed approach increases accuracy and performance.

► We propose a nontrivial semi-automatic approach to solve a problem of contour reconnection in scanned topographical maps. ► The approach refers to the problem of matching end points. ► The main idea of the proposed approach is based on local and geometric properties of contour lines. ► Proposed semi-automatic approach allows users to handle with errors by changing the mask sizes.

Related Topics
Physical Sciences and Engineering Computer Science Computer Vision and Pattern Recognition
Authors
, ,