摘要
提出了一种从图像中精确提取直线特征并定位其端点和方向的新方法,克服了传统边缘跟踪算法的局部性。算法首先跟踪边缘点,递归分割成离散直线段,然后从全局角度合并这些离散的直线段,最后给出了两种鲁棒的直线拟合策略。实验结果表明该算法具有良好的性能,能够适用于较广范围的真实图像。
This paper proposes a new method for linear features extraction and orientation in images, which overcomes the local nature of the conventional line segment grouping approach, while retaining most of its advantages. It tracks edge points, approximates them to piecewise segments using the iterative endpoint fit-and-split algorithm. and groups the discrete line segments from global view. Finally, the paper gives two means for line fitting. The experimental results show that this method has a perfect performance and is suitable to a wide range of real images.
出处
《计算机工程》
EI
CAS
CSCD
北大核心
2006年第13期198-199,202,共3页
Computer Engineering
关键词
直线特征
离散直线段
合并
直线拟合
Linear features
Discrete line segments
Grouping
Line fitting
