彩色扫描地图的自动分色算法研究及实现
Research and Implementation of Automatic Color Segmentation Algorithm for Scanned Color Maps
-
摘要: 对彩色扫描地图图像的色彩误差进行了分析,运用特征向量匹配法对地图上黑版要素进行分层,然后对地图的色彩空间进行转换,并提出了基于二维直方图模糊约束的模糊C-均值(FCM)聚类方法,较好地解决了地图的自动分色问题.该方法已编程实现,效果比较理想.Abstract: Color inaccuracy of a scanned color map is analyzed.To solve this problem,eigenvector line-fitting algorithm is used for black element segmentation.With transformation of the color space,a new effective fuzzy clustering based on fuzzy restraint two-dimension histogram is presented for color elements segmentation. The algorithm has been experimentally verified to be robust and accurate.
下载: