对虚拟人图像数据作多种二维处理，包括图像几何变换、灰度增强、格式转换和压缩、图像配准和分割。
Many methods are used to finish VCH planar image processing, including image geometry transform, gray-scale enhancement format transition and compression , image registration and segmentation.
配准问题的目的就是将同一场景的不同图像对齐或匹配，消除存在的几何畸变。
Basically, the goal of image registration is to align images of same scene by removal of the potential geometrical distortion existed.
图像配准的目的是建立两幅图像间的几何变换关系，去除或减小两幅图像的几何畸变，从而实现图像的几何校正。
The major purpose of registration is to establish geometric transformation between two images, and remove or suppress the geometric distortions between them.
交互式数字图象的配准与镶嵌主要由二个步骤来完成：第一步是由人在显示屏幕上选择确定图像几何位置的控制点集，然后由此确定一幅图像几何变换使两幅图像在几何位置上配准。
Step one is to pick up the control point set which determines the geometric position of images, and then to derive a geometric transform for registering one image to another from those points.
在样本和待配准图像相同几何方向上，先以方向边缘点检测算子检测目标区的数个边缘点作为特征点。
In the same geometrical direction of the sample to be registered and its neighboring images, some edge points are first detected as the characteristic points with directional edge-detection operator.
针对基于属性向量的非线性配准算法，提出用机器学习的方法寻找脑图像中各个点上的最优几何特征向量。
This paper presents a machine learning method to select best geometric features for deformable brain registration for each brain location.
本文提出了两种基于几何约束的图像配准的方法，在图像配准的过程中可以有效地防止错误匹配的传播。
This paper proposes two approaches for image correspondence with geometrical constraints in order to prevent error propagation during image correspondence.
本文提出了两种基于几何约束的图像配准的方法，在图像配准的过程中可以有效地防止错误匹配的传播。
This paper proposes two approaches for image correspondence with geometrical constraints in order to prevent error propagation during image correspondence.
应用推荐