基于DIS边缘检测和自适应边缘生长的图像分割方法

提出一种基于DIS(differenceinstrength)边缘检测和自适应边缘生长的图像分割方法.此方法是边缘检测、边缘生长、区域生长等分割技术的有机结合.通过DIS进行边缘检测,产生了比梯度算子、sobel算子等更完全的边缘信息.为了解决伪边缘及不连续点的问题,提出了自适应的边缘生长方法,较好地解决了该问题,连接了不连续边缘点,产生了边缘点集组成的闭合轮廓.通过进行区域生长,得到了最终的分割结果.实验表明,该分割方法都能获得很清晰可靠的分割效果,提供精确的目标轮廓线.

A new algorithm for image segmentation based on DIS edge detection and adaptive edge growing

A new method of performing image segmentation tasks was developed based on difference in strength (DIS) edge detection and adaptive edge growing technique.This method is an organic combination of edge detection, edge growing and region merging. To detect edges, a DIS technique was applied to obtain more complete edge information than gradient operator,Sobel operator,and other methods. To solve the problem of having the wrong and discontinuous points,an adaptive edge growing technique was proposed. After having connected the discontinuous points, the new adaptive edge growing method produced some closed outlines.Finally the result of segmentation after region growing was attained. The experiment shows this method can provide accurate contours effectively.