基于链码的分水岭算法.ppt

刘旭 A fast Watershed Algorithm based on chain code and its application in image segmentation Watershed algorithm 分水岭算法 主要目的找出集水盆地之间的分水线 常用方法 淹没（浸水）法(flooding)VS算法 降雨法(rainfall) BM算法 New watershed algorithm based on chain code adopt chain code to depict connected components. The new algorithm ?rst simulates raining to generate connected components using chain code instead of pixel address used in Algorithm BM then simulates ?ooding to label catchment basins by tracing chain codes It also only scans image four times, and can segment image completely. Compared with Algorithm BM, the proposed algorithm can describe connected components more clearly, and provides more information to the following processing. 本文实现流程 De?nitions and theorems for chain code Point-out chain code current pixel points to one of the eight neighbor pixels. {0, 1, 2, 3, 4, 5, 6, 7, and 8} De?nitions and theorems for chain code Point-in chain code neighbor pixel points to current pixel. {0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20,0x40, and 0x80} 当前像素和其邻近像素的关系 指出、指入链码的取值就由当前像素和其邻居像素的关系决定。 性质1 图像中任意一个像素到对应的局部极小值点的最陡峭路径都可由该像素开始的一串指出链码表示。 类型I和类型IV像素的指出链码 the point-out chain code of current pixel p should point to the steepest neighbor q 这两种类型的像素有一个共同点，即存在灰度值比自己小的邻居，因此，可令这两类像素的指出链码指向灰度值最小的邻居，如果满足条件的最小邻居不止一个， 则指向第1个最小邻居。 类型II和类型III像素 这两种类型的像素又可以分成以下两类： 灰度值与自己相同的邻近像素已标记指出链码； 都没有标记指出链码。 类型II和类型III像素的指出链码 On the edge of non-minima plateau, these pixels, marked with darker color 灰度值与自己相同的邻近像素已标记指出链码：令像素值与之相同的，且还未标记指出链码的邻居指向当前像素，并标记为深灰色,如图(d)。 若当前像素未标识指出链码，且存在灰度值相同，未标识指出链码的邻居，则先令所有满足此条件的邻居p都指向当前像素,如图(e)。 As for those in minima plateaus, Choose the ?rst pixel in each minima plateau, marked with gray color，and let its neighbors of the same gray value point to it. 性质 2 贮水盆地可从对应的局部极小值点开始的指入链码回溯得到。 实验结果 实验结果 * *