Common tools based on landmarks in medical image elastic registration are Thin Plate Spline (TPS) and Compact Support Radial Basis Function (CSRBF). TPS forces the corresponding landmarks to exactly match each other a...Common tools based on landmarks in medical image elastic registration are Thin Plate Spline (TPS) and Compact Support Radial Basis Function (CSRBF). TPS forces the corresponding landmarks to exactly match each other and minimizes the bending energy of the whole image. However, in real application, such scheme would deform the image globally when deformation is only local. CSRBF needs manually determine the support size, although its deformation is limited local. Therefore, to limit the effect of the deformation, new Compact Support Thin Plate Spline algorithm (CSTPS) is approached, analyzed and applied. Such new approach gains optimal mutual information, which shows its registration result satisfactory. The experiments also show it can apply in both local and global elastic registration.展开更多
In order to study morphological diversity of codling moth, Cydia pomonella （L.） using thin-plate spline analysis, nine geographical populations from four north western provinces of Iran namely East Azarbayjan, West ...In order to study morphological diversity of codling moth, Cydia pomonella （L.） using thin-plate spline analysis, nine geographical populations from four north western provinces of Iran namely East Azarbayjan, West Azarbayjan, Ardebil and Zandjan were collected during 2003 and 2004. 575 and 564 images were prepared from fore and hind wings, respectively. Then 15 and 11 landmarks were determined from fore and hind wings, respectively. With transforming of landmark＇s two dimensional coordinate data into partial warp scores, 26 and 18 scores were generated for fore and hind wings, respectively. Cluster analysis based on wing shape variables using Ward＇s algorithm assigned nine geographical populations into two groups. The pattern of grouping based on fore and hind wings was different in both sexes. Principal component analysis revealed discrimination between geographic populations and confirmed the result of cluster analysis. Among environmental parameters, wind speed showed the highest correlation with wing shape variables. Non significant correlation was observed between geographic and morphological distance matrices as revealed by Mantel test.展开更多
To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. Howeve...To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. However, when the foreground and background share some similar areas in color, the fine segmentation result of conventional interactive methods usually relies on the increase o f manual labels. This paper presents a novel interactive image segmentation method via a regression-based ensemble model with semi-supervised learning. The task is formulated as a non-linear problem integrating two complementary spline regressors and strengthening the robustness of each regressor via semi-supervised learning. First, two spline regressors with a complementary nature are constructed based on multivariate adaptive regression splines （MARS） and smooth thin plate spline regression （TPSR）. Then, a regressor boosting method based on a clustering hypothesis and semi-supervised learning is proposed to assist the training of MARS and TPSR by using the region segmentation information contained in unlabeled pixels. Next, a support vector regression （SVR） based decision fusion model is adopted to integrate the results of MARS and TPSR. Finally, the GraphCut is introduced and combined with the SVR ensemble results to achieve image segmentation. Extensive experimental results on benchmark datasets of BSDS500 and Pascal VOC have demonstrated the effectiveness of our method, and the com- parison with experiment results has validated that the proposed method is comparable with the state-of-the-art methods for in- teractive natural image segmentation.展开更多
The recently proposed weak form quadrature element method （QEM） is applied to flexural and vibrational analysis of thin plates The integrals involved in the variational description of a thin plate are evaluated by a...The recently proposed weak form quadrature element method （QEM） is applied to flexural and vibrational analysis of thin plates The integrals involved in the variational description of a thin plate are evaluated by an efficient numerical scheme and the par- tial derivatives at the integration sampling points are then approximated using differential quadrature analogs. Neither the grid pattern nor the number of nodes is fixed, being adjustable according to convergence need. The C~ continuity conditions char- acterizing the thin plate theory are discussed and the robustness of the weak form quadrature element for thin plates against shape distortion is examined. Examples are presented and comparisons with analytical solutions and the results of the finite element method are made to demonstrate the convergence and computational efficiency of the weak form quadrature element method. It is shown that the present formulation is applicable to thin plates with varying thickness as well as uniform plates.展开更多
基金the National Natural Science Foundation of China (No.60572101) the Natural Science Foundation of Guangdong Province (No.31789).
文摘Common tools based on landmarks in medical image elastic registration are Thin Plate Spline (TPS) and Compact Support Radial Basis Function (CSRBF). TPS forces the corresponding landmarks to exactly match each other and minimizes the bending energy of the whole image. However, in real application, such scheme would deform the image globally when deformation is only local. CSRBF needs manually determine the support size, although its deformation is limited local. Therefore, to limit the effect of the deformation, new Compact Support Thin Plate Spline algorithm (CSTPS) is approached, analyzed and applied. Such new approach gains optimal mutual information, which shows its registration result satisfactory. The experiments also show it can apply in both local and global elastic registration.
文摘In order to study morphological diversity of codling moth, Cydia pomonella （L.） using thin-plate spline analysis, nine geographical populations from four north western provinces of Iran namely East Azarbayjan, West Azarbayjan, Ardebil and Zandjan were collected during 2003 and 2004. 575 and 564 images were prepared from fore and hind wings, respectively. Then 15 and 11 landmarks were determined from fore and hind wings, respectively. With transforming of landmark＇s two dimensional coordinate data into partial warp scores, 26 and 18 scores were generated for fore and hind wings, respectively. Cluster analysis based on wing shape variables using Ward＇s algorithm assigned nine geographical populations into two groups. The pattern of grouping based on fore and hind wings was different in both sexes. Principal component analysis revealed discrimination between geographic populations and confirmed the result of cluster analysis. Among environmental parameters, wind speed showed the highest correlation with wing shape variables. Non significant correlation was observed between geographic and morphological distance matrices as revealed by Mantel test.
基金the National Natural Science Foundation of China （Nos. 61071176, 61171192, and 61272337） and the Doctoral
文摘To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. However, when the foreground and background share some similar areas in color, the fine segmentation result of conventional interactive methods usually relies on the increase o f manual labels. This paper presents a novel interactive image segmentation method via a regression-based ensemble model with semi-supervised learning. The task is formulated as a non-linear problem integrating two complementary spline regressors and strengthening the robustness of each regressor via semi-supervised learning. First, two spline regressors with a complementary nature are constructed based on multivariate adaptive regression splines （MARS） and smooth thin plate spline regression （TPSR）. Then, a regressor boosting method based on a clustering hypothesis and semi-supervised learning is proposed to assist the training of MARS and TPSR by using the region segmentation information contained in unlabeled pixels. Next, a support vector regression （SVR） based decision fusion model is adopted to integrate the results of MARS and TPSR. Finally, the GraphCut is introduced and combined with the SVR ensemble results to achieve image segmentation. Extensive experimental results on benchmark datasets of BSDS500 and Pascal VOC have demonstrated the effectiveness of our method, and the com- parison with experiment results has validated that the proposed method is comparable with the state-of-the-art methods for in- teractive natural image segmentation.
基金supported by the National Natural Science Foundation of China (Grant Nos.51178247 and 50778104)the National High Technology Research and Development Program of China (Grant No.2009AA04Z401)
文摘The recently proposed weak form quadrature element method （QEM） is applied to flexural and vibrational analysis of thin plates The integrals involved in the variational description of a thin plate are evaluated by an efficient numerical scheme and the par- tial derivatives at the integration sampling points are then approximated using differential quadrature analogs. Neither the grid pattern nor the number of nodes is fixed, being adjustable according to convergence need. The C~ continuity conditions char- acterizing the thin plate theory are discussed and the robustness of the weak form quadrature element for thin plates against shape distortion is examined. Examples are presented and comparisons with analytical solutions and the results of the finite element method are made to demonstrate the convergence and computational efficiency of the weak form quadrature element method. It is shown that the present formulation is applicable to thin plates with varying thickness as well as uniform plates.
