摘要
该文基于Hough变换检测直线的基本思想,提出了一种在边缘图像中检测直线的快速算法。该算法首先根据边缘图像中的边缘点统计出可能在直线上的点,再由这些在直线上的候选点和边缘点统计出候选点对应的斜率,由满足条件的候选点与其对应的斜率构成的直线就是从图像中检测出的直线。该算法是根据边缘点分步而不是同时计算统计出直线的两个参数,减少了检测时的计算量。由实验结果,该算法可以快速有效的检测出边缘图像中的直线。
This paper presents an efficient algorithm for detecting straight lines in an edge image.The algorithm is based on the idea of Hough transform,but it results in the two parameters of a straight line by the statistics of all edge points in two steps.First,some points which may be on some lines come out according to the edge points;second,the slopes of lines are calculated by these points and the edge points.The lines made up by the points and corresponding slopes are the result from the edge image.This algorithm reduces the complexity of line detection.The experiment shows the validity of this algorithm.
出处
《杭州电子科技大学学报（自然科学版）》
2007年第6期67-70,共4页
Journal of Hangzhou Dianzi University：Natural Sciences
关键词
直线检测
霍夫变换
边缘检测
line detection
Hough transform
edge detection
