文件名称:grid_segmentation.zip
介绍说明－－下载内容均来自于网络，请自行研究使用
This paper presents a novel segmentation algorithm for metallographic images, especially those objects without regular boundaries and homogeneous intensity. In metallographic quantification, the complex microstructures make the conventional approaches hard to achieve a satisfactory partition. We formulate the segmentation procedure as a new fr a mework of iterative watershed region growing constrained by the ridge information. The seeds are selected by an effective double-threshold approach, and the ridges are superimposed as the highest waterlines in watershed transform. To tackle the over-segmentation problem, the blobs are merged iteratively with the utilization of Bayes classification rule. Experimental results show that the algorithm is effective in performing segmentation without too much parameter tuning.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
压缩包 : grid_segmentation.zip 列表 Iterative Watersheding.pdf grid segmentation/ grid segmentation/Thumbs.db grid segmentation/test.m grid segmentation/startup.m grid segmentation/readme.txt grid segmentation/ridge/ grid segmentation/ridge/im_hessangle2.m grid segmentation/ridge/im_hessstrflt2.m grid segmentation/ridge/im_scalablehess2.m grid segmentation/ridge/nonmaxsup.m grid segmentation/ridge/bwridgecenter.m grid segmentation/ridge/RemovePseudoContour.m grid segmentation/ridge/ModifyWaterShed.m grid segmentation/ridge/MarkPseudoBlob.m grid segmentation/ridge/gray2bw.m grid segmentation/ridge/dspimcat.m grid segmentation/ridge/dspimanalys.m grid segmentation/ridge/dspimalpha.m grid segmentation/ridge/DrawEllipse.m grid segmentation/ridge/DepthMeature.m grid segmentation/data1/ grid segmentation/data1/wkd01.jpg grid segmentation/data1/wkd02.jpg grid segmentation/data1/wkd03.jpg grid segmentation/data1/wkd04.jpg grid segmentation/data1/wkd05.jpg grid segmentation/data1/result/ license.txt