| 飞机蒙皮缺陷磁光图像识别算法研究 |
| |
| 引用本文： | 高庆吉,王祥凤,崔鹏,牛国臣,邢志伟.飞机蒙皮缺陷磁光图像识别算法研究[J].中国民航学院学报,2006,24(1):28-31. |
| |
| 作者姓名： | 高庆吉 王祥凤 崔鹏 牛国臣 邢志伟 |
| |
| 作者单位： | [1]中国民用航空学院航空地面特种设备研究基地,天津300300 [2]东北电力学院自动化学院,吉林132012 [3]天津市智能信号与图象处理重点实验室,天津300300 |
| |
| 基金项目： | 天津市智能信号与图像处理重点实验室基金 |
| |
| 摘 要： | 提出一种基于模糊支持向量机自动识别飞机蒙皮磁光图像中铆钉裂纹缺陷的新方法。针对铆钉磁光图像的不规则圆形特点．采用阈值法确定近似铆钉区域中心，将由中心发出的星形射线矢量作为识别的基本特征，采用模糊支持向量机方法对铆钉周围裂纹的方向进行分类。其中，支持向量机采用径向基核函数，利用网格法选取核宽度惩罚常数．并结合模糊隶属度函数解决多类分类问题中存在的错分、拒分现象。样本测试实验结果表明，算法具有很高的识别率。
|
| 关 键 词： | 飞机蒙皮缺陷识别 支持向量机 星形矢量法 核函数模型 模糊隶属度 |
| 文章编号： | 1001-5000(2006)01-0028-04 |
| 收稿时间： | 2005-09-27 |
| 修稿时间： | 2005-12-21 |
Research on Algorithm of Aircraft Skin Defect Recognition Through Magneto Optic Image |
| |
| GAO Qing-ji,WANG Xiang-feng,CUI Peng,NIU Guo-chen,XING Zhi-wei.Research on Algorithm of Aircraft Skin Defect Recognition Through Magneto Optic Image[J].Journal of Civil Aviation University of China,2006,24(1):28-31. |
| |
| Authors: | GAO Qing-ji WANG Xiang-feng CUI Peng NIU Guo-chen XING Zhi-wei |
| |
| Institution: | 1.CAAC Aviation Ground Special Equipment Research Base,CAUC,Tianjin 300300,China; 2.Department of Automatic Control Englneering,Northeast China Institute of Electric Power Engineering,Jilin 132012,China; 3.Tianjin Key Lab for Advanced Signal and Image Processing, Tianjin 300300,China |
| |
| Abstract: | To detect the aircraft surface defect through magneto optic image,a new recognition algorithm based on the fuzzy support vector machine(FSVM) is presented.Considering the irregular cycle character of rivet's magneto optic image,threshold method is used to get the approximate center of rivet region,and star radial vector emitted from this center is taken as the recognition basic feature,and FSVM classifies the direction of cracks around rivets.Thereinto,radial basis kernel function is selected in the SVM,cross-validation and fuzzy membership function(FMF) are used for higher recognition ability.SVM mode is optimized by utilizing cross-validation method and the wrong and refusal recognition problems are solved through FMF in multi-classifier.Experiment on test samples proves high recognition ability. |
| |
| Keywords: | aircraft skin defect recognition support vector machine star-vector-method kernel function model fuzzy membership function |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
