图像处理中处理重叠椭圆轮廓的改进算法

Improved Algorithm for Processing Oval Contour in Image Processing

为了提取数字图像处理中重叠椭圆的真实轮廓信息,将一种改进的K-means聚类法和图像轮廓凹点筛选方法相结合。新方法相比已有的重叠椭圆检测算法,能提高处理复杂重叠椭圆轮廓的能力,并明显提升了图像轮廓凹点检测方法的鲁棒性。新算法有较好的稳定性,提取的重叠椭圆轮廓信息与真实轮廓误差明显减小。

In order to extract the real contour information of overlapping ellipses in digital image processing,this paper combines an improved K-means clustering method with the image contour pits filter method.Compared with the existing overlapping ellipse detection algorithm,the method can improve the ability of dealing with complex overlapping elliptical contour and significantly improve the robustness of the image contour pitting detection method.The experimental results showed that the proposed algorithm has good stability,the error between the extracted elliptical contour information and the real contour is significantly reduced.