梯度方向

利用梯度方向信息的随机Hough变换

A randomized Hough transform using gradient direction information

采用拟梯度方向信息的随机Hough变换直线检测

Randomized Hough Transform with Imitative Gradient Direction

MeanShift就是偏移的均值向量，指向概率密度梯度方向。

Mean Shift is the mean vector , direction of which is just the gradient of probability density .

材料和方法：选取21名正常志愿者，随机分为3组：b值组、弥散敏感梯度方向组和层厚/层间距组。

Material and methods : Diffusion tensor imaging of the cerebral white matter fiber was performed in 21 healthy adult volunteers , who are randomly divided into three groups .

结论豆状核信号强度及其ADC值不受弥散梯度方向影响；

Conclusion ADC and signal intensity in lentiform nucleus were not affected by diffusion gradient directions .

基于形状结构和梯度方向加权的Hausdorff距离图像匹配方法

A Novel Hausdorff Distance Weighted by Shape Structure and Gradient Direction for Image Matching

基于梯度方向直方图（HOG）的目标检测方法已经被证明具备足够的鲁棒性和良好的检测效果，也适合于工程化。

The detection algorithm based on HOG has been proved which has enough robustness and good results of detection .

TWINSPAN和DCA分析显示，河岸植物群落呈现沿湿度梯度方向的分布格局。图2表3参8。

TWINSPAN and DCA indicated that riparian plant communities distributed along the gradient of moisture .

以GA优化BP网络的初始权值和阈值，按负梯度方向修正网络权值及阈值，对网络进行训练。

First , the initialized weights and threshold of BP neural network ( BPNN ) was optimized with GA , and the network was trained by modifying the weights and threshold in the negative gradient direction .

目的研究人脑不同弥散梯度方向弥散加权像（DWI）上豆状核及放射冠的表现特征。

Purpose To study the characteristics on diffusion weighted imaging ( DWI ) with different diffusion gradient directions in lentiform nucleus and in corona radiata .

方法对20名成年健康志愿者行头部扩散张量成像，比较不同扫描参数（层厚/层间距、b值及扩散敏感梯度方向数）对图像质量的影响。

Methods Diffusion tensor imaging of the head was performed in 20 healthy adult volunteers . Different parameters including slice thickness , b value and the number of the diffusion sensitive gradient direction were applied and their impaction on the quality of the images were compared .

该算法利用图像边缘的梯度方向信息，很好地解决了一般Hough变换的无效累积问题，可以快速检测出圆心坐标。

The cumulation in common Hough transform can be greatly solved by using gradient direction information of image edge , and the coordinates of the center of circle can be quickly detected .

采用两种尺度、有部分重叠的小块来进行梯度方向的直方图统计，并在梯度方向统计时进行向量分解来改进SIFT算法的特征描述子生成方式。

By using two kinds of size , partly overlapped small regions to calculate the gradient direction histogram , and decomposing the gradient , the feature descriptor generation method is improved .

为了测试算法在不同描述符下的性能，采用了梯度方向直方图、光流方向直方图、时空Haar特征三种描述符并对构建方法进行了详细阐述。

To test the algorithm performance under different descriptors , histogram of gradient , histogram of optical flow orientation and spatial-temporal Haar feature were used in this step .

方法利用不同弥散梯度方向对50例正常人脑施加平面回波弥散加权成像检查，测量豆状核及放射冠的信号强度及其表观弥散系数（ADC值）。

Methods DW EPI with different diffusion gradient directions was performed in 50 healthy volunteers . The signal intensity and apparent diffusion coefficient ( ADC ) were measured in lentiform nucleus and in corona radiata from multidirection echo planar diffusion weighted images .

将光刀曲线的法线方向简化为灰度的梯度方向，在该方向上利用灰度重心法求取光刀中心，省去了求Hessian矩阵以确定法向的繁琐计算。

With this method , the normal direction of the stripe can be simplified to the gray level gradient , avoiding thus complicated steps for calculating a Hessian matrix to get the normal direction .

针对这些特性本文在研究原有的交通标志分割与检测技术的基础上提出一种基于颜色不变量和塔式梯度方向直方图（PHOG）特征的交通标志检测方法。

In this paper we propose a new traffic sign detection method based on color invariants and pyramid histogram of oriented gradients ( PHOG ) features .

为了检测单幅红外图像中的人体目标，提出了一种基于金字塔梯度方向直方图（PHOG）特征的分步骤人体检测方法。

In order to detect human targets in single infrared image , a Pyramid of Histograms of Orientation Gradients ( PHOG ) - based step-by-step human detection algorithm is proposed .

激光介质的热效应对激光的光束质量有着严重的影响，板条激光介质可以利用Zig-Zag光路周期性穿越温度梯度方向以减小热聚焦及应力双折射效应。

Thermal effects of laser medium have a serious effect on laser beam quality , slab laser medium can reduce the thermal focusing and stress birefringence effect by the light going through temperature gradient direction with a Zig-Zag optical path periodically .

改进的RHT主要是利用精度要求不高的梯度方向信息来决定是否对采样到的两点进行参数计算和累积来解决无效积累的问题，而且还将梯度方向信息用于直线和椭圆确认，减少运算量。

In the improved RHT , gradient direction information , of which precision is not required to be high , is used to determine whether the parameter should be accumulated or not . In comparison with the basic RHT , the problem of useless accumulations is well solved .

本文首次将Kirsch边缘梯度方向分解应用到汉字识别上。3、在特征融合方面：汉字的结构特征能够反映出其全局特性，而统计特征又能反映出其局部特性。

This paper applications the Kirsch edge gradient directional decomposition to the Chinese character recognition for the first time . 3 , in the feature fusion : the structural feature of the Chinese characters can reflect its global characteristics , and the statistical feature can reflect its local characteristics .

心肌细胞兴奋与电场梯度方向的关系

The Relationship Between Cardiac Excitation and the Electrical Potential Gradient Directions

基于边缘梯度方向直方图的中国静态手语识别

Chinese Static Sign Language Recognition Based on Edge Gradient Direction Histogram

心肌组织兴奋对电场梯度方向的依赖性

Dependence of cardiac excitation on the direction of electrical potential gradient field

提出了一种基于地形梯度方向的山脊线和山谷线的提取方法，该方法从理论上进一步完善了地形高程断面极值法。

The new method perfect terrain profile analysis method theoretically .

基于梯度方向双边对称性的旋转人脸中心跟踪

Face Center Tracking Based on Bilateral Symmetry of Gradient Direction

基于地形梯度方向的山脊线和山谷线的提取

Extraction of Ridge and Valley from DEM Based on Gradient

基于梯度方向直方图特征的多核跟踪

Multiple Kernels Based Object Tracking Using Histograms of Oriented Gradients

基于梯度方向直方图的快速人体检测算法

Fast Human Detection Based on Histogram of Oriented Gradients

基于共轭梯度方向的CP-BP算法在变压器油中溶解气体诊断法中的应用

On the application of CP BP algorithm for DGA NN diagnosis in power transformer