一种基于连通区域的轮廓提取方法
收稿日期: 2010-08-02
修回日期: 2010-11-10
网络出版日期: 2011-06-25
基金资助
江苏省自然科学基金资助项目（BK2009667）；江苏省高校自然科学基金资助项目(08KJB520001)；江苏省“青蓝工程”资助项目
An Approach to Contour Extraction Based on Connected Regions
Received date: 2010-08-02
Revised date: 2010-11-10
Online published: 2011-06-25
轮廓提取在许多智能视觉系统中被认为是非常重要的过程，其结果的正确性和可靠性直接影响到机器视觉系统对客观世界的理解。而现有诸多边缘检测的方法都存在着各自的局限性和不足之处，为此本文提出一种利用最佳阈值分割和基于连通区域面积阈值化的实现算法，可以同时实现噪声消除与轮廓提取，并据此定位图像中的物体目标。实验结果显示，只要噪声面积没有超过物体面积，应用该算法不仅可以完全消除噪声，而且能得到连续的无交叉的单像素宽度的物体轮廓，且轮廓不变形。
关键词： Otsu 法; 单像素宽度的物体轮廓; 噪声消除
王文豪,周泓,严云洋 . 一种基于连通区域的轮廓提取方法[J]. 计算机工程与科学, 2011 , 33(6) : 67 -71 . DOI: 10.3969/j.issn.1007130X.2011.
Contour extraction is one of the fundamental steps in computer vision. The correctness and reliability of its results affect directly the comprehension of machine vision systems for the objective world. There are many contour algorithms at present, and each has its own characteristics and shortcomings. Therefore, this paper gives an algorithm based on the connected regions and the threshold to not only extract the contour of the object but also erase the noise at the same step in image processing. Furthermore, the object can be located according to the contour. As shown in the experiments, the noises are erased clearly when the area of each noise is less than that of the object, and especially a single pixel width contour of the object can be presented which is also noninterval and noncross, and not distorted from the object.
［1］邹柏贤,林京壤.图像轮廓提取方法研究［J］.计算机工程与应用，2008, 44(25):161165.
［2］娄联堂. 基于图像二分法的封闭轮廓提取方法［J］.计算机工程与应用，2006, 42(13):8486.
［3］Bao P, Zhang L,Wu X. Canny Edge Detection Enhancement by Scale Multiplication［J］.IEEE Trans on Pattern Analysis and Machine Intelligence, 2005,27(9):14851490.
［4］严云洋,盛明超,杨静宇.单像素宽度目标轮廓提取的实现［J］.微计算机信息，2007(19):284286.
［5］ZHANG YANG, ROCKETT P I. The Bayesian Operating Point of the Canny Edge Detector［J］.IEEE Trans on Image Processing, 2006,15(11):34093416.
［6］Bao P,Zhang L. Noise Reduction for Magnetic Resonance Image via Adaptive Multiscale Products Thresholding［J］.IEEE Trans on Medical Imaging, 2003,22(9):10891099.
［7］Kiranyaz S, Ferreira M. Gabbouj M. Automatic Object Extraction over Multiscale Edge Field for Multimedia Retrieval［J］.IEEE Trans on Image Processing, 2006,15(12):375377.
［8］王卫星,王李平,吴志超. 一种基于最大类间后验概率的Canny边缘检测算法［J］.计算机应用，2006, 29(4):962965.
［9］Jiao S,Li X, Lu X.An Improved Ostu Method for Image Segmentation［C］∥Proc of the 8th Int’l Conf on Signal Processing, 2006:147163.
［10］李华强,喻擎苍,方玫.Canny算子中Otsu阈值分割法的运用［J］.计算机工程与设计, 2008, 29(9):22972299.
［11］王红艳,严云洋.火灾图像边缘检测和轮廓提取算法研究［J］.科技信息, 2007(35):108109.
［12］HU DONG, TIAN XIANGZHONG. A MultiDirections Algorithm for Edge Diction Based on Fuzzy Mathematical Morphology［C］∥Proc of the 16th Int’l Conf on Artificial Reality and TelexistenceWorkshops,2006:361364.
/
| 〈 |
|
〉 |