用两步Hough变换检测圆

Hough变换在图像处理中占有重要地位，是一种检测曲线的有效方法。但使用传统的Hough变换来检测圆,具有存储空间大计算时间长的缺点。为此提出了采用两步Hough变换的圆检测方法，利用圆的斜率特性，降低了Hough参数空间的维度，提高了运算效率，并推广到椭圆的检测之中。

Using tow-steps Hough transform to detection ellipses

Hough transform plays an important part in the image processing. It is an effective approach for curve detection. But using traditional Hough transform to detect circles has the disadvantages of massive storage requirement and high cost of computation. This article presented a method of tow-steps Hough transform to decide whether the input figure is a circle. The method utilized the slope attribute of circle to reduce the statistical dimension of Hough parameter space, enhance the operating efficiency and advance to detect an ellipse.