提出一种新的轮廓特征点提取方法，它利用最小二乘法拟合轮廓曲线，结合斜率、曲率信息提取特征点。
A new feature-points extraction algorithm is proposed, which USES least square method fitting contour curve and combines slope, curvature information to extract feature-points.
针对组合形状零件几何尺寸测量中的关键问题—轮廓识别，提出了一种基于弧长的轮廓特征点提取的方法。
An approach to extract feature points on the boundary based on length of arc is proposed in view of the key problem of measuring composite-shape parts.
然后根据特征点的几何定义，利用轮廓线的位置、曲率等信息自动提取特征点。
Characteristic points can be extracted by considering the geometry definition, the position and curvature of each point on the contours.
根据特征点的几何定义，利用轮廓线的位置信息、曲率等属性来提取特征点。
Lastly, the characteristic points can be extracted by the geometry definition of them and the position and curvature of each point on the contours.
本系统建了一个包含50个人脸图象的数据库，实验结果表明这种方法可以有效地获取头部轮廓和人脸特征点。
A database involving 50 images of human face is built up by this system. Head outline and feature points of human face can be effectively achieved by this method, as shown by experimental results.
提出了一种新的目标轮廓特征级融合方法，求解两类模式图像的收敛动态轮廓线控制点向量差的范数平方极小化。
A new feature level fusion method of target's contour was proposed, which minimizes norm's square of the difference of control point vectors of convergent dynamic contours in two modal images.
曲面内腔类零件的反求有别于轮廓外形的反求，主要体现在数据采集的方法，点云的处理，特征点的提取以及曲线的拟合。
The reverse of lumen part is different from outline, such as collect data method, treat with point, pick up feature point and curve fitting.
根据各特征点对轮廓的贡献，采用弦长加权拟合法对轮廓点进行处理，从而得到轮廓的中心位置。
The points were set different weight for their different effect on the center of the contour in fitting process.
结果表明，该方法计算简单，以较少的关键点实现了对向量字轮廓的较好拟合，基本保持了字形特征。
The result shows that this method is very simple and can make better approach of vector contour character with less critical point, and it also can keep the character of vector contour characters.
研究了心脏左室轮廓光流场检测的一种聚类中心特征点匹配算法。
The paper discusses the detections for contour-based optical flow field of the LV of heart. The detection is an application of matching algorithm of boundary cluster centers.
研究了心脏左室轮廓光流场检测的一种聚类中心特征点匹配算法。
The paper discusses the detections for contour-based optical flow field of the LV of heart.
本文首先提出了一种保持轮廓形状特征的自适应特征点采样算法，该算法大大减少了后续处理的的存储量和计算量。
First, this paper presents a shape-keeping and adaptive feature points sampling algorithm, which can reduce storage and computational requirments in the post-processing procedure.
用统计学的方法，等角度间隔地计算归一化步态轮廓图像各像素点至质心距离的均值与方差，并用其构造步态识别的特征向量。
Using statistical methods to calculate the Angle interval mean and variance of pixels to centroid distance of the normalized gait silhouette images, and construct them as a feature vector.
描述形状的重要特征是物体的轮廓曲线，为了提高识别效率，通常使用控制点表达轮廓。
An important feature of shape description is the contour curves of object. To improve the efficiency of recognition, dominant points are usually used to represent the contour.
人脸特征点定位就是对人脸的形状和人脸局部特征(如眉毛、眼睛、鼻子和嘴巴等)的位置、关键点或轮廓线进行描述。
It can provide the description for face shape and the information of the local features, such as eyebrows, eyes, nose, mouth and so on.
然后检测输入图像中物体上的特征点，形成特征轮廓，并与特征轮廓模型相匹配，就可得到该物体在三维空间中的姿态；
The feature points distributed on the 3D model surface of an object are detected to create a feature-outline model for fast alignment between the 3D model and its real intensity image.
首先结合几何约束与曲率信息定位特征点，根据特征点确定人脸对称面，提取人脸侧面轮廓线。
Then the symmetrical plane of 3D face is determined based on the feature points, and the profile is determined by the obtained symmetrical plane.
首先结合几何约束与曲率信息定位特征点，根据特征点确定人脸对称面，提取人脸侧面轮廓线。
Then the symmetrical plane of 3D face is determined based on the feature points, and the profile is determined by the obtained symmetrical plane.
应用推荐