基于格式塔完形规则的闭合轮廓提取方法  

Closed Contour Extraction Method Based on Gestalt Rules

作　　者：曾接贤[1] 王玉[1] 

机构地区：[1]南昌航空大学计算机视觉研究所,南昌330063

出　　处：《南昌航空大学学报（自然科学版）》2015年第2期1-9,50,共10页Journal of Nanchang Hangkong University(Natural Sciences)

基　　金：国家自然科学基金(61165011);江西省教育厅科研项目(GJJ12427);江西省青年科学基金(20132BAB211021)

摘　　要：针对传统基于格式塔完形规则的轮廓提取易受到背景上边缘影响,导致轮廓提取的准确率低问题,提出一种新的基于格式塔完形规则的闭合轮廓提取方法。首先,为减少边缘提取过程中提取的背景边缘,给出了融入显著性约束的Canny边缘检测方法,即在Canny边缘提取的框架中,融入显著性约束;接着,针对Canny边缘检测方法检测到的边缘易受噪声影响问题,提出一种融入边缘信息的折线逼近边缘拟合算法;然后,采用格式塔完形规则中的闭合性对拟合边缘进行度量,得到边缘之间的闭合关系;最后,通过分析边缘间的闭合关系与区域的显著性,设计了一个边缘闭合的代价函数,并利用最小权值最优匹配算法求解代价函数,得到最终的闭合轮廓。实验结果表明,该算法提高了轮廓提取的有效性和准确性。In this paper, a new closed contour extraction method based on Gestalt rules is proposed to reduce the impact on the background of the edge. Firstly, the integration significant constraint Canny edge detection method, which integrates significant constraints in the framework of Canny edge detection, is given to reduce the background edge in edge extraction process. Then, edge information into the edge fitting algorithms about the fold approximation is proposed to reduce the effects of noise to the edge by Canny edge detection method. Moreover, the edge of the fitting is measured by Closed Rules in Gestalt rules, which can obtain the relationship between the edges. Finally, the new objective function is proposed by analyzing the relationship between the edges and the significance of the target area, the objective function is solved by the minimum weight perfect matching algorithms. Experimental results show that our algorithm improves the effectiveness and accuracy of the contour extraction.

关 键 词：闭合轮廓提取 格式塔完形规则 显著性 边缘拟合 目标函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]