摘要
经验Ridgelet变换具有方向选择性和自适应分解能力,2DPCA可直接利用原始图像构建协方差矩阵。结合经验Ridgelet变换和2DPCA的各自优点,提出了一种基于经验Ridgelet-2DPCA金属断口图像识别方法。同时将提出的方法与Ridgelet-2DPCA、经验Ridgelet-PCA识别方法相比较,实验结果表明,提出的方法中的二维固有模态分量比Ridgelet系数具有更丰富的特征信息,2DPCA相比于PCA,图像结构信息更加完整,因而,提出的经验Ridgelet-2DPCA的金属断口识别方法取取得了比经验Ridgelet-PCA、Ridgelet-2DPCA更好的识别效果。
The empirical ridgelet transform has the ability of direction selectivity and adaptive decomposition. 2 DPCA can directly use the original image toconstruct the covariance matrix. Combined with the advantages of Empirical ridgelet transform and 2 DPCA, anidentification method ofmetal fracture based onempirical ridgelet-2 DPCA. At the same time, the proposed method is compared with the Ridgelet-2 DPCA, Ridgelet-PCA recognition method. The experimental results show that the bidimensional intrinsic mode Function(BIMF) component has more abundant feature information than ridgelet coefficient. 2 DPCA has more complete image structure informationthan PCA. Therefore, the proposed empirical Ridgelet-2 DPCA has achieved better recognition effect than experience Ridgelet-PCA and Ridgelet-2 DPCA recognition method.
引文
[1] 张莉,黎明,杨小芹.基于树形小波变换的断口图像识别[J].南昌航空大学学报(自然科学版),2007,21(2):42-45.ZHANG Li,LI Ming,YANG XiaoQin.Recognition of fracture image based on tree wavelet transform[J].Journal of Nanchang Hangkong University (Natural Science Edition),2007,21(2):42-45 (In Chinese)
[2] 徐飞.金属断口SEM图像的特征提取与分析[D].成都:电子科技大学,2006:36-46.XU Fei.Feature extraction and analysis of metal fracture SEM image[D].Chengdu:University of Electronic Science and Technology of China,2006:36-46 (In Chinese).
[3] 梁鹏,李志农,基于Contourlet-RVM航构件断口图像识别方法研究[J].机械强度,2013(4):4-8.LIANG Peng,LI ZhiNong.Recognition method of fracture image ofaerial material based on contourlet transform and relevance vector machine[J],Journal of Mechanical Strength,2013,35 (4):395-399 (In Chinese)
[4] 李志农,陈康,闫敬文.基于Grouplet-KPCA金属断口图像识别方法研究[J].机械强度,2016(1):1-5.LI ZhiNong,CHENG Kang,YAN JingWen,Recognition method of metal fracture image based on Grouplet-KPCA[J],Journal of Mechanical Strength,2016(1):1-5 (In Chinese).
[5] E.J.Candes,Ridgelets:estimating with ridge functions,The Annals of Statistics,2003,31(5):1561-1599.
[6] 李艳玲.伪极傅立叶变换理论及应用研究[D].西安:西安电子科技大学,2009:19-25.LI YanLing.The theory and application of pseudo polar FFT transform[D].Xi’an Electronic and Science University,2009:19-25 (In Chinese) .
[7] Gilles J.Empirical Wavelet Transform[J].IEEE Transactions on Signal Processing,2013,61(16):3999-4010.
[8] Gilles J,Tran G,Osher S.2D Empirical Transforms.Wavelets,Ridgelets and Curvelets revisited[J].Siam Journal on Imaging Sciences,2014,7(7):157-186.
[9] Yang J,Zhang D,Frangi A F,et al.Two-dimensional PCA:a new approach to appearance-based face representation and recognition.[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2004,26(1):131
[10] Liu S,Luo M.Face recognition based on 2DPCA and DWT[C].Cross Strait Quad-Regional Radio Science and Wireless Technology Conference.IEEE,Harbin City,China,2011:1459-1462.
[11] Hui M,Hu F.The study of human face recognition basedcurvelet transform and 2DPCA[C]International Conference on Information Science and Engineering.IEEE,Zhengzhou City,China,2011:5512-5515.