基于曲线二叉树的微弱边缘检测方法

Faint edge detection approach based on curve binary tree

针对传统边缘检测算法对微弱边界检测性能弱且时间复杂度高的问题,提出一种有效的微弱边缘检测算法。利用二进制分割的方法建立曲线二叉树,构建多尺度匹配滤波器;利用自下而上搜索策略检测可能的边缘曲线;根据检测阈值分配边缘曲线得分,确定检测的边缘。模拟加噪图像、自然景观图像、生物医学真实图像的实验结果验证了提出方法的有效性,与传统方法相比,其微弱边缘检测性能大幅度提高,具有更强的抗噪性能。

Aiming at the problems that the traditional edge detection approaches suffer from the poor performance of detecting faint edge and the time-complexity is high,an effected edge detection approach for faint edge was proposed.The hierarchical binary partition was adopted to establish a curve binary tree,and to build multiple-scale matched filer.The bottom-up fashion was used to detect possible edge curves.Scores for the possible curves were allocated according to detection threshold to achieve the corrected edge.The effectiveness of the proposed method was verified by the experimental results of simulated noisy images,natural landscape images and biomedical real image.Experimental results also show that,compared with the traditional methods,the proposed method can get better edge detection effects for faint edge with better noise immunity.