Object-based change detection has been the hotspot in remote sensing image processing.A new approach toward object-based change detection is proposed.The two different temporal images are unitedly segmented using the ...Object-based change detection has been the hotspot in remote sensing image processing.A new approach toward object-based change detection is proposed.The two different temporal images are unitedly segmented using the mean shift procedure to obtain corresponding objects.Then change detection is implemented based on the integration of corresponding objects’ intensity and texture differences.Experiments are conducted on both panchromatic images and multispectral images and the results show that the integrated measure is robust with respect to illumination changes and noise.Supplementary color detection is conducted to determine whether the color of the unchanged objects changes or not when dealing with multispectral images.Some verification work is carried out to show the accuracy of the proposed approach.展开更多
针对手指静脉图像中存在的弱边缘、灰度不均匀以及低对比度等现象,提出一种结合偶对称Gabor滤波与水平集思想的分割算法,并应用于手指静脉图像的分割。首先,使用偶对称Gabor滤波算法,对手指静脉图像从8个不同的方向分别进行滤波运算;然...针对手指静脉图像中存在的弱边缘、灰度不均匀以及低对比度等现象,提出一种结合偶对称Gabor滤波与水平集思想的分割算法,并应用于手指静脉图像的分割。首先,使用偶对称Gabor滤波算法,对手指静脉图像从8个不同的方向分别进行滤波运算;然后,根据8个方向上的滤波结果进行图像重建,得到目标与背景灰度对比度显著提高的图像;最后,应用结合局部与全局信息的水平集方法对手指静脉图像进行分割。将所提算法与Li等水平集算法(LI C,HUANG R,DING Z,et al.A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity.MICCAI'08:Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention,Part II.Berlin:Springer,2008:1083-1091)、Legendre水平集(L2S)算法相比,所提算法在分割精度评价标准面积差异(AD)百分比上分别降低了1.116%、0.370%,相对差异度(RDD)分别降低了1.661%、1.379%。实验结果表明,与传统只考虑局部信息或全局信息的水平集图像分割算法相比,所提算法能取得更高的分割精度。展开更多
This article introduces a new normalized nonlocal hybrid level set method for image segmentation.Due to intensity overlapping,blurred edges with complex backgrounds,simple intensity and texture information,such kind o...This article introduces a new normalized nonlocal hybrid level set method for image segmentation.Due to intensity overlapping,blurred edges with complex backgrounds,simple intensity and texture information,such kind of image segmentation is still a challenging task.The proposed method uses both the region and boundary information to achieve accurate segmentation results.The region information can help to identify rough region of interest and prevent the boundary leakage problem.It makes use of normalized nonlocal comparisons between pairs of patches in each region,and a heuristic intensity model is proposed to suppress irrelevant strong edges and constrain the segmentation.The boundary information can help to detect the precise location of the target object,it makes use of the geodesic active contour model to obtain the target boundary.The corresponding variational segmentation problem is implemented by a level set formulation.We use an internal energy term for geometric active contours to penalize the deviation of the level set function from a signed distance function.At last,experimental results on synthetic images and real images are shown in the paper with promising results.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.40601084,40801178)National High Technology Research & Development Program of China("863"Program)(Grant Nos.2007AA120203,2009AA12Z145)
文摘Object-based change detection has been the hotspot in remote sensing image processing.A new approach toward object-based change detection is proposed.The two different temporal images are unitedly segmented using the mean shift procedure to obtain corresponding objects.Then change detection is implemented based on the integration of corresponding objects’ intensity and texture differences.Experiments are conducted on both panchromatic images and multispectral images and the results show that the integrated measure is robust with respect to illumination changes and noise.Supplementary color detection is conducted to determine whether the color of the unchanged objects changes or not when dealing with multispectral images.Some verification work is carried out to show the accuracy of the proposed approach.
文摘针对手指静脉图像中存在的弱边缘、灰度不均匀以及低对比度等现象,提出一种结合偶对称Gabor滤波与水平集思想的分割算法,并应用于手指静脉图像的分割。首先,使用偶对称Gabor滤波算法,对手指静脉图像从8个不同的方向分别进行滤波运算;然后,根据8个方向上的滤波结果进行图像重建,得到目标与背景灰度对比度显著提高的图像;最后,应用结合局部与全局信息的水平集方法对手指静脉图像进行分割。将所提算法与Li等水平集算法(LI C,HUANG R,DING Z,et al.A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity.MICCAI'08:Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention,Part II.Berlin:Springer,2008:1083-1091)、Legendre水平集(L2S)算法相比,所提算法在分割精度评价标准面积差异(AD)百分比上分别降低了1.116%、0.370%,相对差异度(RDD)分别降低了1.661%、1.379%。实验结果表明,与传统只考虑局部信息或全局信息的水平集图像分割算法相比,所提算法能取得更高的分割精度。
基金supported in part by the National Natural Science Foundation of China(11626214,11571309)the General Research Project of Zhejiang Provincial Department of Education(Y201635378)+3 种基金the Zhejiang Provincial Natural Science Foundation of China(LY17F020011)J.Peng is supported by the National Natural Science Foundation of China(11771160)the Research Promotion Program of Huaqiao University(ZQN-PY411)Natural Science Foundation of Fujian Province(2015J01254)
文摘This article introduces a new normalized nonlocal hybrid level set method for image segmentation.Due to intensity overlapping,blurred edges with complex backgrounds,simple intensity and texture information,such kind of image segmentation is still a challenging task.The proposed method uses both the region and boundary information to achieve accurate segmentation results.The region information can help to identify rough region of interest and prevent the boundary leakage problem.It makes use of normalized nonlocal comparisons between pairs of patches in each region,and a heuristic intensity model is proposed to suppress irrelevant strong edges and constrain the segmentation.The boundary information can help to detect the precise location of the target object,it makes use of the geodesic active contour model to obtain the target boundary.The corresponding variational segmentation problem is implemented by a level set formulation.We use an internal energy term for geometric active contours to penalize the deviation of the level set function from a signed distance function.At last,experimental results on synthetic images and real images are shown in the paper with promising results.
