摘要
提出了基于全局最小二乘拟合的应用于二维图像的直线抽取算法.类似于一维数据曲线拟合的方法,通过引入叉分的手段,克服了二维图像数据非单值函数的困难(图像的y坐标作为x坐标的函数),实现了用最小二乘算法来全局地描述、提取二维图像中的直线.并提供了数值实验验证.
Based on global least squares fitting, an algorithm of extracting straight lines on the two-dimensional picture is proposed. Similar to curve fitting on the one-dimensional data, the difficulty has overcome that the function of two-dimensional picture is multi-valued ( the y coordinate as the x coordinate), with the help of forked method; and it realizes the global description and extraction of the straight lines in the two-dimensional picture using the least squares algorithm. The experiment shows that this algorithm is effective.
出处
《集美大学学报(自然科学版)》
CAS
2008年第3期255-260,共6页
Journal of Jimei University:Natural Science
基金
国家自然科学基金资助项目(60772164)
福建省自然科学基金资助项目(A0540005)
关键词
直线抽取
直线拟合
非单值的
叉分
extracting straight lines
straight line fitting
multi-valued
forking