摘要
椭圆检测是模式识别中的一个重要领域,传统的基于Hough变换的椭圆检测方法耗时长、效率低。本文给出了一种高效的椭圆检测方法,该方法利用椭圆的闭合边界及对偶点对信息,能够快速、准确地计算出椭圆参数。该方法首先对椭圆进行边缘检测,然后进行边界跟踪,形成椭圆边界链码,消除噪声及非闭合的数据,然后在链码上寻找对偶点对,根据对偶点对进行Hough变换,算出椭圆的形心、长半轴、短半轴及椭圆倾斜角等参数。实验结果表明,该方法具有速度快,占用内存小及检测性能好等优点。
In the field of pattern recognition, ellipse detection is the key teclmology to improve image matching veracity and automation degree, The method of traditional ellipse detection based on Hough transformation has disadvantage of long time and low efficiency. In this paper, a high efficient ellipse detection approach is introduced. The parameters of ellipse can be calculated fast and efficiently based on edge-tracking and symmetry-point information of ellipse. We detect the edge of ellipse first, then track the edge of it, and acquired the ellipse＇s edge-chain. At last, we remove the noise and isolated point. Symmetry-point is found in edge-ohain, Hough transformation is processed based on symmetry-point. Ellipsc＇s ccnter point, major axis, minor axis and direction magic are calculated. The result of elhpse detection shows that tills method has tie advantages of high speed, small storage and high detection performance.
出处
《长春理工大学学报（自然科学版）》
2010年第3期133-136,共4页
Journal of Changchun University of Science and Technology(Natural Science Edition)
关键词
椭圆检测
边界跟踪
HOUGH变换
图像处理
ellipse detection
edge-tracking
Hough transformation
image processing
