Contour lines are the most important features to characterize three dimensional terrain on two dimensional map sheets. Different from a well conditioned map

aliasing and false colors in the scan of a common conditioned map are so serious that when to segment contour lines from it

many gaps due to contour lines intersecting and overlapping with other features become more intricate. In this paper an effective method for extracting contour lines from color scanned topographical maps is proposed. It focuses on reconnecting gaps of contour lines. In topographical maps segmentation

an eigenvector fitting algorithm is used for computing the color keys ofmap features( include contour lines) and the phenomena of color alias and color misalignment are greatly reduced. In contour lines reconnection

linear features extracted from the gray version of the input colormap are utilized to repair the contour lines segments extracted from the input colormap. Unlike the existing methods

it introduces corresponding solutions for different cases ofgaps in contour lines. Finally

some representative samples and national standard topographic maps with a scale of 1∶50

000 are tested

and an evaluation scheme for the results is provided. The experiments indicate good applicability of this method in applications.