Impact of Scanning Quality on Deep Learning-Based Contour Vectorization from Topographic Maps

The quality of scanned topographic maps—including parameters such as image compression, scanning resolution, and bit depth—may strongly influence the performance of deep learning models for contour vectorization. In this study, we investigate this dependence by training eight U-Net models on the same map data but under varying input quality conditions. Each model is trained to segment contour lines from the raster input, followed by a postprocessing pipeline that converts segmented output into vector contours. We systematically compare the models with respect to topological error metrics (such as contour intersections and dangling ends) in the resulting vector output and overlay metrics of matched contour segments within given tolerance. Our experiments demonstrate that while the input data quality indeed matters, moderate lowering of quality parameters doesn’t introduce significant practical tradeoff, while storage and computational requirements remain low. We discuss implications for the preparation of archival map scans and propose guidelines for choosing scanning settings when the downstream goal is automated vectorization. Our results highlight that deep learning methods, though resilient against reasonable compression, remain measurably sensitive to degradation in input fidelity.