This paper presents an approach to extract the elevation layers from a color-coded relief scanned map having as an input information the colors provided by the map's legend. We work in the CIE L{sup}*u{sup}*v{sup}* color space. The mean shift filtering is used to reduce the printing details (the dithering effect). The colors are extracted from the legend by the Randomised Local Search (RLS) algorithm. The elevation layers are identified by computing the Euclidean distance between each color in the legend and each pixel in the scanned image and then using a threshold operation. Overlaps between the extracted layers are also considered in order to eliminate distortions.
展开▼
机译：本文提出了一种从颜色编码的浮雕扫描地图中提取高度层的方法，其具有由地图的图例提供的颜色提供的输入信息。我们在CIE L {SUP} * U {sup} * v {sup} *上工作。平均移位过滤用于减少打印细节（抖动效果）。通过随机本地搜索（RLS）算法从图例中提取颜色。通过计算图例中的每个颜色与扫描图像中的每个像素之间的欧几里德距离来识别升降层，然后使用阈值操作来识别。还考虑提取的层之间的重叠以消除扭曲。
展开▼
