文件名称：Automatic segmentation of cells from microscopic imagery using ellipse detection
文件大小：1.07MB
文件格式：PDF
更新时间：2012-03-07 16:23:09
医学图像处理 椭圆检测
Cell image segmentation is a necessary first step of many automated biomedical imageprocessing procedures. There certainly has been much research in the area. To this, a new method has been added, which automatically extracts cells from microscopic imagery, and does so in two phases. Phase 1 uses iterated thresholding to identify and mark foreground objects or ‘blobs’ with an overall accuracy of .97%. Phase 2 of the method uses a novel genetic algorithms-based ellipse detection algorithm to identify cells, quickly and reliably. The mechanism, as a whole, has an accuracy rate .96% and takes ,1 min (given our specific hardware configuration) to operate on a microscopic image.