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
MEMS gyroscopes are widely used in the underwater vehicles owing to their excellent performance and affordable costs.However,the temperature sensitivity of the sensor seriously affects measurement accuracy.Therefore,i...MEMS gyroscopes are widely used in the underwater vehicles owing to their excellent performance and affordable costs.However,the temperature sensitivity of the sensor seriously affects measurement accuracy.Therefore,it is significantly to accurately identify the temperature compensation model in this paper,the calibration parameters were first extracted by using the fast calibration algorithm based on the Persistent Excitation Signal Criterion,and then,MEMS gyro temperature compensation model was established by utilizing the thin plate spline interpolation method,and the corresponding identification results were compared with the results from the polynomial fitting method.The effectiveness of the proposed algorithm has been validated through the comparative experiment.展开更多
In order to achieve refined precipitation grid data with high accuracy and high spatial resolution,hourly precipitation grid dataset with 1 km spatial resolution in Anhui Province from May to September (in the rainy s...In order to achieve refined precipitation grid data with high accuracy and high spatial resolution,hourly precipitation grid dataset with 1 km spatial resolution in Anhui Province from May to September (in the rainy season) in 2016 and from August 2017 to July 2018 was established based on thin plate smoothing spline (TPS),which meets the needs of climate change research and meteorological disaster risk assessment.The interpolation errors were then analyzed.The grid precipitation product obtained based on thin plate smoothing spline,CLDAS-FAST and CLDAS-FRT were evaluated.The results show that the interpolated values of hourly precipitation by thin plate smoothing spline are close to the observed values in the rainy season of 2016.The errors are generally below 0.9 mm/h.However,the errors of precipitation in the mountainous areas of eastern Huaibei and western Anhui are above 1.2 mm/h.On monthly scale,the errors in June and July are the largest,and the proportion of absolute values of the errors ≥2 mm/h is up to 2.0% in June and 2.2% in July.The errors in September are the smallest,and the proportion of absolute values of the errors ≥2 mm/h is only 0.6%.The root mean square (RMSE) is only 0.37 mm/h,and the correlation coefficient (COR) is 0.93.The interpolation accuracy of CLDAS-FRT is the highest,with the smallest RMSE (0.65 mm/h) and mean error ( ME =0.01 mm/h),and the largest COR (0.81).The accuracy of the precipitation product obtained by thin plate smoothing spline interpolation is close to that of CLDAS-FAST.Its RMSE is up to 0.80 mm/h,and its ME is only -0.01 mm/h.Its COR is 0.73,but its bias (BIAS) is up to 1.06 mm/h.展开更多
扭曲的文档图像会干扰文档图像的光学字符识别(Optical Character Recognition,OCR).为了对扭曲形变的文档图像进行矫正,提高扭曲文档识别的正确率,基于目标检测与分割的网络,提出文档图像的边缘检测方法,使用贝塞尔(Bezier)曲线拟合文...扭曲的文档图像会干扰文档图像的光学字符识别(Optical Character Recognition,OCR).为了对扭曲形变的文档图像进行矫正,提高扭曲文档识别的正确率,基于目标检测与分割的网络,提出文档图像的边缘检测方法,使用贝塞尔(Bezier)曲线拟合文档图像的边缘曲线,通过目标检测的算法回归Bezier曲线的控制点.将文档图像的边缘检测转化为边缘曲线Bezier控制点的回归,使用文档的边缘点计算扭曲文档矫正后的矩形模板,然后将文档图像通过薄板样条插值(Thin Plate Spline,TPS)算法重映射到矩形模板中,完成文档的矫正.实验结果表明,提出的矫正方法能够对扭曲文档进行精确的边缘提取,和其他算法相比,经该算法矫正后的文档图像,其OCR的正确率有较大的提升.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MEMS gyroscopes are widely used in the underwater vehicles owing to their excellent performance and affordable costs.However,the temperature sensitivity of the sensor seriously affects measurement accuracy.Therefore,it is significantly to accurately identify the temperature compensation model in this paper,the calibration parameters were first extracted by using the fast calibration algorithm based on the Persistent Excitation Signal Criterion,and then,MEMS gyro temperature compensation model was established by utilizing the thin plate spline interpolation method,and the corresponding identification results were compared with the results from the polynomial fitting method.The effectiveness of the proposed algorithm has been validated through the comparative experiment.
基金Supported by New Technology Integration Project of Anhui Meteorological Bureau(AHXJ201704)Project for Masters and Doctors of Anhui Meteorological Bureau(RC201701)
文摘In order to achieve refined precipitation grid data with high accuracy and high spatial resolution,hourly precipitation grid dataset with 1 km spatial resolution in Anhui Province from May to September (in the rainy season) in 2016 and from August 2017 to July 2018 was established based on thin plate smoothing spline (TPS),which meets the needs of climate change research and meteorological disaster risk assessment.The interpolation errors were then analyzed.The grid precipitation product obtained based on thin plate smoothing spline,CLDAS-FAST and CLDAS-FRT were evaluated.The results show that the interpolated values of hourly precipitation by thin plate smoothing spline are close to the observed values in the rainy season of 2016.The errors are generally below 0.9 mm/h.However,the errors of precipitation in the mountainous areas of eastern Huaibei and western Anhui are above 1.2 mm/h.On monthly scale,the errors in June and July are the largest,and the proportion of absolute values of the errors ≥2 mm/h is up to 2.0% in June and 2.2% in July.The errors in September are the smallest,and the proportion of absolute values of the errors ≥2 mm/h is only 0.6%.The root mean square (RMSE) is only 0.37 mm/h,and the correlation coefficient (COR) is 0.93.The interpolation accuracy of CLDAS-FRT is the highest,with the smallest RMSE (0.65 mm/h) and mean error ( ME =0.01 mm/h),and the largest COR (0.81).The accuracy of the precipitation product obtained by thin plate smoothing spline interpolation is close to that of CLDAS-FAST.Its RMSE is up to 0.80 mm/h,and its ME is only -0.01 mm/h.Its COR is 0.73,but its bias (BIAS) is up to 1.06 mm/h.
文摘扭曲的文档图像会干扰文档图像的光学字符识别(Optical Character Recognition,OCR).为了对扭曲形变的文档图像进行矫正,提高扭曲文档识别的正确率,基于目标检测与分割的网络,提出文档图像的边缘检测方法,使用贝塞尔(Bezier)曲线拟合文档图像的边缘曲线,通过目标检测的算法回归Bezier曲线的控制点.将文档图像的边缘检测转化为边缘曲线Bezier控制点的回归,使用文档的边缘点计算扭曲文档矫正后的矩形模板,然后将文档图像通过薄板样条插值(Thin Plate Spline,TPS)算法重映射到矩形模板中,完成文档的矫正.实验结果表明,提出的矫正方法能够对扭曲文档进行精确的边缘提取,和其他算法相比,经该算法矫正后的文档图像,其OCR的正确率有较大的提升.
基金中国科学院知识创新重要方向项目"黄土高原水土保持的区域环境效应"(KZCX3-SW-421)中澳合作项目ACIAR PROJECT"Regional impacts of re-vegetation on water resources of the Loess Plateau+1 种基金China and Middle and Upper Murrumbidgee CatchmentAustralia"(LWR1/2002/018)
