改进的多尺度顺序边缘连接检测法及在医学图像中的应用

Improved Multiresolution Sequential Edge Linking and Its Application in Medical Image

边缘提取是图像处理与分析中的基本问题 ,由 Purdue大学的 Edward JDelp等人提出的多尺度顺序边缘连接检测法 (Multiresolution Sequential Edge L inking,MSEL )在保持边缘的连接性、较小的错误率等许多方面优于其它的边缘提取方法 .但是 ,它在初值选取上不尽合理 ,该文有效地解决了这一问题 ,并给出了在医学图像应用中的实验结果 .

Edge detection is the basic operation in image processing and analysis. Multiresolution Sequential Edge Linking (MSEL), which is proposed by Edward J. Delp of Purdue University, has a number of advantages over other edge detection schemes. One such advantage is the lower false alarm rate while maintaining full connectivity of the edge. However, the choosing of the initial value is not reasonable. This paper improves the MSEL method and gives some test images. The results show the efficiency of the improvement.