Please wait a minute...
J4  2011, Vol. 45 Issue (6): 1013-1020    DOI: 10.3785/j.issn.1008-973X.2011.06.008
自动化技术、计算机技术     
多分辨轮廓匹配的成型制件外形检测
毛锋, 张树有, 施岳定
浙江大学CAD&CG国家重点实验室,浙江 杭州 310027
Shape detection for molding products based on
multi-resolution contour matching
MAO Feng, ZHANG Shu-you, SHI Yue-ding
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要:

为了通过对制件图像进行轮廓匹配实现外形异常识别,提高生产效率和产品质量,提出制件外形多分辨轮廓匹配检测技术,通过分析起点对轮廓曲线的各分辨率小波变换的影响,建立轮廓某尺度下小波逼近量的搜索匹配策略,实现粗匹配下的形变判定.研究匹配轮廓段局部特征以及轮廓区间对的相异度统计,进而获得轮廓点对的精确对准,达到轮廓精配准,实现飞边、缺损等缺陷类型判定,最终得出外形检测结果.该方法在多种制件图像、各种外形异常类型中进行应用验证,结果表明外形检测准确度满足要求.

Abstract:

A method of shape detection was proposed to match the shape of products to achieve anomaly recognition, thereby improve the production efficiency and products quality. The affection of starting point to the multi-resolution wavelet transformation was studied, and a searching and matching strategy of the wavelet approximation at an certain scale was established to achieve rough matching. Then, the local features of contour segments and the dissimilarity statistics of pairs of contours were used to achieve the precise matching of contour detects, and then realize the judgment of types of defects such as flash and short shot. The final detection result was obtained through previous two steps. The method was verified by the experiments including several kinds of products and different shape anomalies.

出版日期: 2011-07-14
:  TP 391.41  
基金资助:

教育部博士点基金资助项目(200803350031);浙江省自然科学基金重点资助项目(Z1080339).

通讯作者: 张树有,男,教授,博导.     E-mail: zsy@zju.edu.cn
作者简介: 毛锋(1984—),男,硕士生,从事CAD、图像处理、机器视觉等研究.E-mail:rickymf2007@zju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

毛锋, 张树有, 施岳定. 多分辨轮廓匹配的成型制件外形检测[J]. J4, 2011, 45(6): 1013-1020.

MAO Feng, ZHANG Shu-you, SHI Yue-ding. Shape detection for molding products based on
multi-resolution contour matching. J4, 2011, 45(6): 1013-1020.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.06.008        https://www.zjujournals.com/eng/CN/Y2011/V45/I6/1013

[1] 丁险峰,吴洪,张宏江,等.形状匹配综述[J].自动化学报,2001,27(5): 678-694.
DING Xianfeng, WU Hong, ZHANG Hongjiang, et al. Review on shape matching[J]. Acta Automatica Sinica, 2001,27(5): 678-694.
[2] 胡硕,朱明,吴川.结合Zernike矩的多尺度模板形状匹配[J].光电工程,2005,32(10): 35-38.
HU Shuo, ZHU Ming, WU Chan. Shape matching based on multiscale template with Zerinike moments[J]. OptoElectronic Engineering, 2005,32(10): 35-38.
[3] LONCARIC S, DHAWAN A P. Nearoptimal MST based shape description using genetic algorithm[J]. Pattern Recognition,1995, 28: 571-579.
[4] 石旭利,肖广,羊子格,等.改进的多分辨率形状匹配算法研究[J].中国图象图形学报,2006,11(11): 1661-1664.
SHI Xuli, XIAO Guang, YANG Zige, et al. An improved algorithm for shape matching based on multiresolution[J]. Journal of Image and Graphics, 2006,11(11): 1661-1664.
[5] 张文景,许晓鸣,苏键锋.基于Hausdorff距离的2D形状匹配改进算法[J].中国图象图形学报,2000,5(2): 106-109.
ZHANG Wenjing, XU Xiaoming, SU Jianfeng. An improved algorithm for 2D shape matching based on Hausdorff distance[J]. Journal of Image and Graphics, 2000,5(2): 106-109.
[6] JUN Xie, HENG P A, SHAH M. Shape matching and modeling using skeletal context[J].Pattern Recognition, 2008, 41(5): 1756-1767.
[7] 王斌,舒华忠,施朝健,等.一种基于轮廓线的形状描述与匹配方法[J].电子与信息学报,2008,30(4): 949-953.
WANG Bin, SHU Huazhong, SHI Chaojiao, et al. A contour based shape description and matching method[J]. Journal of Electronics & Information Technology, 2008,30(4): 949-953.
[8] 刘曙,罗予频,杨士元.基于多尺度的轮廓匹配方法[J].计算机工程,2008,34(1): 201-203.
LIU Shu, LUO Yupin, YANG Shiyuan. Contour matching algorithm based on multiscaler shape[J]. Computer Engineering, 2008,34(1): 201-203.
[9] 张国敏,殷建平,祝恩.基于极坐标区间运算的2D形状匹配[J].计算机研究与发展,2008,45(S1): 286-290.
ZHANG Guomin, YIN Jianpin, ZHU En, et al. 2D shape matching based in polar interval operations[J]. Journal of Computer Research and Development, 2008,45(S1): 286-290.
[10] LATECKI L J, MEGALOOIKONOMOU V, WANG Qiang, et al. An elastic partial shape matching technique[J]. ComputerAided Design, 2008,40(6): 708-720.
[11] MORI G, BELONGIE S, MALIK J. Efficient shape matching using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(11): 1832-1837.
[12] SOO Y H, UK L S, MU L K. Recognition of 2D object contours using startingpointindependent wavelet coefficient matching [J].Journal of Visual Communication and Image Representation,1998,9(2): 171-181.

[1] 杨玉婷, 史玉回, 夏顺仁. 基于讨论机制的头脑风暴优化算法[J]. J4, 2013, 47(10): 1705-1711.
[2] 朱晓恩, 郝欣, 夏顺仁. 基于Levy flight的特征选择算法[J]. J4, 2013, 47(4): 638-643.
[3] 周水琴, 应义斌, 商德胜. 基于形态学的香梨褐变核磁共振成像无损检测[J]. J4, 2012, 46(12): 2141-2145.
[4] 孙创日,甄帅,夏顺仁. 基于吸引区域的多模态脑磁共振图像仿射配准[J]. J4, 2012, 46(9): 1722-1728.
[5] 谢迪, 童若锋, 唐敏, 冯阳. 具有高区分度的视频火焰检测方法[J]. J4, 2012, 46(4): 698-704.
[6] 戴渊明, 韦巍, 林亦宁. 基于颜色纹理特征的均值漂移目标跟踪算法[J]. J4, 2012, 46(2): 212-217.
[7] 李启雷, 金文光, 耿卫东. 基于无线惯性传感器的人体动作捕获方法[J]. J4, 2012, 46(2): 280-285.
[8] 刘晨彬,潘颖,张海石,黄峰平,夏顺仁. 基于磁共振图像的脑瘤MGMT表达状况检测算法[J]. J4, 2012, 46(1): 170-176.
[9] 钱诚, 张三元. 适用于目标跟踪的加权增量子空间学习算法[J]. J4, 2011, 45(12): 2240-2246.
[10] 曹颖, 郝欣, 朱晓恩, 夏顺仁. 基于自动随机游走的乳腺肿块分割算法[J]. J4, 2011, 45(10): 1753-1760.
[11] 吕谷来, 李建平, 李锵, 俞利兴, 朱松明, 楼建忠, 袁祎琳. 基于机器视觉的砧木定位识别方法[J]. J4, 2011, 45(10): 1766-1770.
[12] 赖小波,朱世强. 基于互相关信息的非参数变换立体匹配算法[J]. J4, 2011, 45(9): 1636-1642.
[13] 刘建明, 鲁东明, 葛蓉. 基于全局优化的图像修复及其在GPU上实现[J]. J4, 2011, 45(2): 247-252.
[14] 王金德, 寿黎但, 李晓燕, 陈刚. 基于多重分割捆绑特征的目标图像检索[J]. J4, 2011, 45(2): 259-266.
[15] 战江涛,刘强,柴春雷. 基于三维模型与Gabor小波的人脸特征点跟踪方法[J]. J4, 2011, 45(1): 30-36.