基于区域特征和连接成分的地图规范化算法

地图图像规范化算法是使地图图像同类型对象的某种属性具有相同的表现形式的一种方法或过程，它是地理信息识别的一个重要步骤。根据彩色栅格城市交通地图图像中各类地理要素的特征，提出一种基于区域特征和连接成分的地图图像规范化算法。首先对地图图像中的区域特征进行分析，并建立区域识别测度，实现了区域颜色规范化；再通过对非区域对象的连接成分进行分析，并建立道路识别测度，在区域颜色规范化的基础上，实现了道路颜色规范化。实验结果表明，对于彩色城市交通地图图像，该算法取得了良好的效果。

A Normalizing Algorithm for Urban Traffic Map Image Based on Region Features and Connected Component

A normalizing algorithm for color raster urban traffic map image is a method or process which makes one of properties of the same type object uniform in the map image, it is an important step for recognition and extraction of geographical information. Based on the dissimilar features of the different geographical dements, a normalizing algorithm is put forward on the basis of region features and connected component of others than regions. The algorithm includes two key steps. First of all, the region features are analyzed and a measure is established to recognize regions, then a region normalizing procedure is set up. Afterwards, a measure is brought forware to recognize roads on the basis of the cormected component, and then a road normalizing process is proposed. Experiments show that the algorithm proposed in the paper performs effectively for the color raster urban traffic map images.