您现在的位置: 首页> 研究主题> 梯度矢量流

梯度矢量流

梯度矢量流的相关文献在2000年到2022年内共计87篇,主要集中在自动化技术、计算机技术、临床医学、机械、仪表工业 等领域,其中期刊论文79篇、会议论文4篇、专利文献141454篇;相关期刊58种,包括中国医学物理学杂志、中国图象图形学报、计算机仿真等; 相关会议4种,包括第十六届全国图象图形学学术会议 暨第六届立体图象技术学术研讨会、第七届全国信号与信息处理联合会议暨首届全国省(市)级图象图形学会联合年会、第六届全国信息获取与处理学术会议等;梯度矢量流的相关文献由208位作者贡献,包括范延滨、刘彩霞、刘焜等。

梯度矢量流—发文量

期刊论文>

论文:79 占比:0.06%

会议论文>

论文:4 占比:0.00%

专利文献>

论文:141454 占比:99.94%

总计:141537篇

梯度矢量流—发文趋势图

梯度矢量流

-研究学者

  • 范延滨
  • 刘彩霞
  • 刘焜
  • 周寿军
  • 孙蕾
  • 张荣国
  • 张雪飞
  • 潘振宽
  • 董育宁
  • 俞海平
  • 期刊论文
  • 会议论文
  • 专利文献

搜索

排序:

年份

    • 沈梦洁; 潘振宽; 宋金涛; 魏伟波
    • 摘要: 针对自排斥Snake模型对于狭窄图像区域作用力不足,传统加性算子分裂方法计算复杂,内存用量也会随着图像大小的增加而迅速增长等问题,提出了在原模型的基础上增加梯度矢量流有向力场,以加快轮廓线在图像狭窄区域的演化速度,并为改进的模型设计快速对偶算法以简化算法设计,提高求解效率。数值实验表明,改进模型及算法在计算效率方面较经典模型及算法有较大提高。
    • 卢印举; 豆艳艳; 戴曙光; 苏玉
    • 摘要: 针对裂缝形态多样性和分布随机性使得传统裂缝图像分割算法的泛化能力弱的问题,提出一种基于几何结构测度的路面裂缝图像分割算法。首先,采用瑞利分布和高斯分布对裂缝图像背景和目标进行建模,并用期望最大化算法求解裂缝灰度混合模型参数;然后,通过高斯核函数与图像的卷积计算裂缝的边界映射,用梯度矢量流场构造裂缝图像Hessian矩阵,由Hessian矩阵描述裂缝测度函数并获取裂缝多尺度特征向量;最后,将裂缝多尺度特征向量和灰度混合模型融合到马尔可夫随机场,基于最小能量准则,利用条件迭代算法求解裂缝最大标号场来实现裂缝图像分割。实验表明,与仅依靠灰度特征的传统裂缝图像分割算法相比,所提算法综合指标达88.02%、重叠率达54.92%,优于其他算法,具有良好的噪声抑制能力和泛化能力。
    • 付永清; 张宪民
    • 摘要: Based on the griadient vector flow, a topological contour extraction approach for compliant mechansimsis proposed.Firstly, element node densities are computed by a density redistribution.Then, the grads of node densities are obtained by the difference method.Subsequently, the external energy and triditional enternal force and griadient vector flow.During the evolving process of the model, bilinear interpolation is used to calculate the griadient vector flow of a random point, Aiming to different position of holes in the topology, different initialization and evolving methods for the model are developed, So automation contour extraction for the topologies of compliant mechanisms is realized.At last, numerical examples are used to confirm the feasibiligy of the proposed approach.%提出一种基于梯度矢量流模型的柔顺机构拓扑图的轮廓提取方法.该方法首先通过密度再分配求出单元节点密度,然后,利用差分方法计算出单元节点密度的梯度,之后,相继求出节点的外能、传统外力和梯度矢量流.在模型演化过程中,利用双线性插值算法求出任意点的GVF,同时,针对拓扑图的孔所处的不同位置,给出了不同的初始模型及相应的模型演化方法,实现了柔顺机构拓扑图轮廓的自动提取.最后,数值算例表明了文中算法的可行性.
    • 吴军; 李丽; 喻玲娟
    • 摘要: GVF Snake模型在边缘检测和图像分割中应用广泛.GVFSnake模型相比于传统的Snake模型有更大的捕捉区域和更好的分割性能.然而,GVFSnake模型在分割带有尖角的目标时曲线很难收敛到尖角处.针对GVF Snake模型的不足之处,本文提出角点信息和GVF Snake模型相结合的图像分割方法.首先,运用基于边缘轮廓曲率的角点检测方法,检测出图像中的真实角点,局部修正GVF场,然后结合角点信息给出局部角点力,最后将角点力与修正后的GVF场相结合的得出一种新的外力.实验证明,本文改进的GVF Snake模型能够更好的收敛到图像的尖角处.%GVF snake model is used widely in edge detection and image segmentation.GVF Snake model has larger capture range and better segmentation performance than traditional Snake model.However,the GVF method is inaccurate in capturing the sharp comer of the object during image segmentation.To solve the inadequate of GVF Snake,a new technique of GVF Snake model based on angular point information to extract boundaries of objects having sharp corners is presented.First,we check the real corner points at the edge using curvature-based comer detector,and locally modified GVF force field.Then local angular point force is put forwarded based on comer information.Finally,combining the comer force and the modified external force of the GVF Snake,a new external force of improved GVF Snake is proposed.Experiments indicate that the new algorithm have a better convergence to the sharp comers.
    • 王敏; 王培光; 王娜; 宗晓萍
    • 摘要: 图像分割指的是从待分割图像中提取感兴趣的目标.进一步对目标进行跟踪分析等应用.Snake活动轮廓模型不同于传统的分割方法.本文在传统Snake模型的基础上运用GVF Snake模型进行图像目标处理,克服了手动绘制初始轮廓显得缺陷,实现自动确定活动轮廓模型的初始轮廓并进行连续迭代分割图像.通过对不同目标进行实验,验证了该算法的优越性.
    • 胡小为; 刘宏申; 徐国雄; 阮越; 刘恒; 潘祥
    • 摘要: 由于CV(Chan-Vese)模型是一个非凸性泛函,对该泛函求极值只能得到局部最优解,运用该模型进行图像分割时,很难在全局范围内得到理想的结果。鉴于此,提出一种结合梯度矢量流(gradient vector flow, GVF)和CV模型的水平集图像分割方法。该方法通过GVF将边缘梯度信息扩散至整幅图像,在保留CV模型基本优点的同时,融入GVF的全局性梯度信息,从而引导CV模型在全局范围内演化至准确的目标边缘。实验结果表明,该方法的分割效果和收敛速度均明显优于传统CV模型。%Owning to the non-convex functional of with the Chan-Vese(CV) model, one can only obtain a local optimal solution. It is difficult to achieve an ideal result for image segmentation in the global range. Therefore a new level set based image segmentation method that combining CV model and gradient vector flow(GVF) was proposed. The edge gradient information is spreaded to the entire image with GVF, which guides the evolution of CV model to the correct target edge in the global range and retains the basic advantages of CV model. The experimental results indicate that the present method are obviously better than the traditional CV model.
    • 费勤水; 张榆锋; 陆玉婧; 章克信; 万国盛; 崔龙芳
    • 摘要: 提取超声图像的轮廓对医学诊断有着积极意义。然而,由于超声图像具有目标与背景间对比度低、信噪比低等特点,以往的边缘检测算法在解决图像噪声、精确定位边缘以及获得连续光滑的边缘线之间的矛盾均未得到理想的效果。GVF snake能较好地解决以上矛盾,且具有更大的捕获范围和更强的凹陷域收敛性。但GVF snake初始轮廓线需手工勾勒,不仅比较繁琐,而且目标提取的结果在很大程度上受人工初始化的影响。为此,提出一种多尺度小波变换模极大值与GVF snake算法结合的方法来提取颈部淋巴结超声图像轮廓。该方法首先运用小波变换模极大值多尺度边缘检测算法得到目标图像的边缘图,再在边缘图上分别选取上、下、左、右四个不同方向若干个特征点,即可自动获得较为客观的初始轮廓线,最后利用GVF snake模型提取图像的精确轮廓。实验表明该方法能得到目标图像连续光滑的轮廓线,同时比GVF snake提取的轮廓更加精确,更能反映轮廓的局部细节。此外,由于初始轮廓更加接近给定图像的真实边缘,从而减少了梯度矢量流力场迭代(GVF)次数,提高了轮廓的收敛速度。%It is of positive significance to extract the contour of ultrasound images for medical diagnosis.However,since the ultrasound images have low resolution and SNR,all previous edge detection algorithms cannot achieve ideal effects on overcoming the contradiction between removing image noise,precisely positioning the edge and obtaining continuous and smooth contour lines.GVF snake model can well solve the contradiction above,and has a larger capture range and stronger sag exposed area convergence.However the initial contour of GVF snake must be hand-sketched,it is cumbersome and the results of object extraction are heavily influenced by artificial initialisation. Therefore,we propose a method which combines the multi-scale wavelet transform modulus maxima with GVF snake algorithm to extract the contour of cervical lymph node ultrasound image.First,the method uses wavelet transform modulus maxima multi-scale edge detection algorithm to obtain the edge chart of object image,and then it selects a number of characteristic points from four different directions of upper, lower,left and right,thus can automatically get a rather objective initial contour line.Finally,it uses the GVF snake model to extract the precise contour of the image.Experiments show that the method makes the contour line of the object image smooth and continuous;the contour it extracted is more accurate compared with the GVF snake model,and better reflects local details.In addition,since the initial contour is more approximate to real edge of the given image,thus it reduces the iteration numbers of gradient vector flow (GVF)field and improves the convergence speed of the contour.
    • 陈立潮; 牛玉梅; 潘理虎; 张秀琴
    • 摘要: 为进一步理解Snake模型,首先以归类方式系统地总结了Snake模型的各种改进模型及其最新应用状况;在此基础上,讨论了Snake模型的研究难点和发展趋势.分析结果表明,虽然Snake各种改进模型和基本Snake模型有较大的差异,但其研究思想一脉相承.此外,可针对各种改进模型的优缺点将其应用到不同场景中.
    • 黄淑英; 杨勇
    • 摘要: 针对各向异性扩散冲击滤波器(ADSF)在图像增强中对噪声敏感的问题,将梯度矢量流(GVF)引入到ADSF中,提出一种新的图像去噪方法GVF-ADSF.在改进的GVF-ADSF方法中,通过引入曲率差来区分图像的特征区域,并定义一个加权系数来控制滤波器中2个扩散项在图像的边缘区域和平坦区域的扩散程度,使得图像区域之间能够自然的平滑过渡.通过实验对比本文方法与均值滤波、Perona and Mailk(PM)模型、ADSF模型的去噪性能,结果表明所提方法能很好地去除图像噪声并保留图像丰富的纹理细节,得到更高的信噪比.
  • 查看更多

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号