一种新的多尺度边缘跟踪算法及其应用

针对多尺度边缘检测中如何有效地将不同尺度上的边缘信息相融合问题,提出了一种新的多尺度边缘跟踪算法。该方法首先获得输入图像的多尺度边缘图像和多尺度梯度方向图,然后根据相邻尺度间对应边缘点的相似特征,进行由大尺度到小尺度的逐层边缘跟踪,将不同尺度上的边缘信息融合,最后通过对获得的跟踪边缘图像的细化处理得到最终边缘图像。实验结果表明,该融合算法具有边缘检测完整、定位准确、伪边缘点少等优点,并且具有较高的运行效率。...

Full description

Saved in:

Bibliographic Details
Published in	计算机应用研究 Vol. 32; no. 12; pp. 3801 - 3804
Main Author	陈恩庆王建波齐林
Format	Journal Article
Language	Chinese
Published	郑州大学信息工程学院,郑州,450000 2015
Subjects	多尺度Sobel方法多尺度边缘图像梯度方向图滞后阈值处理边缘跟踪 edge tracking 梯度方向图 M-Sobel 边缘跟踪多尺度边缘图像滞后阈值处理 multi-scale edge image hysteresis threshold processing 多尺度Sobel方法 gradient orientation map
Online Access	Get full text
ISSN	1001-3695
DOI	10.3969/j.issn.1001-3695.2015.12.065

Cover

More Information
Summary:	针对多尺度边缘检测中如何有效地将不同尺度上的边缘信息相融合问题,提出了一种新的多尺度边缘跟踪算法。该方法首先获得输入图像的多尺度边缘图像和多尺度梯度方向图,然后根据相邻尺度间对应边缘点的相似特征,进行由大尺度到小尺度的逐层边缘跟踪,将不同尺度上的边缘信息融合,最后通过对获得的跟踪边缘图像的细化处理得到最终边缘图像。实验结果表明,该融合算法具有边缘检测完整、定位准确、伪边缘点少等优点,并且具有较高的运行效率。
Bibliography:	51-1196/TP Chen Enqing, Wang Jianbo, Qi Lin （ School of Information Engineering, Zhengzhou University Zhengzhou 450000, China ） In order to snlve the problem thai how to effectively fusion edges from different scales in mnhi-scale edge detection, this paper proposed a novel multi-scale edge tracking algorithm. First,tile proposed method obtained the input image＇ s multi-scale edge images and gradient orientation maps. Second,based on the similar characteristics of the corresponding edge points of the adjacent scales,this algorithm improved the resnhs of edge detection by perfomfing coarse-to-fine edge tracking. Finally,this approach obtained the final edge image, after refinement processing. Experimental results indicate that the proposed algorithm has the advantages of edge integrity and positioning accuracy,and has fewer false edge points. Moreover,it also has high efficiency. edge tracking; muhi-scale edge image; gradient orientation map; M-Sobel; hvsteresis threshold processing
ISSN:	1001-3695
DOI:	10.3969/j.issn.1001-3695.2015.12.065