该表示形式中没有权因子和额外的控制参数，而且具有几何不变性、仿射不变性等良好性质。
The representation has no weight factors or control parameters, and it is geometric and affine invariant.
实验表明，改进后的算法继承了SIFT算法对图像缩放、旋转等不变性，而且增强了图像对视角的仿射不变性，极大地改善了匹配效果。
The experimental results show that this algorithm is as robust as SIFT, but also acquires good performance on affine invariance of view point change, improves matching results greatly.
提出一种快速、有效的图家匹配算法，算法中采用的特征矢量具有RST不变性，可以对发生仿射变换的图象直接进行特征匹配。
The feature vector in the algorithm is RST invariant, which makes the feature matching operate directly on the image having geometry switch.
为了实现长基线图像特征点的立体匹配，提出了一种新的基于特征点仿射变换不变性的匹配算法。
In order to provide the feature points stereo matching between two wide baseline images, a novel algorithm based on affine invariant feature of the feature points is proposed.
这个功能实现了模糊图像梯度点的局部变化的部分不变性，如仿射或三维投影。
The features achieve partial invariance to local variations, such as affine or 3D projections, by blurring image gradient locations.
证明了新的数据深度在保持原深度其他性质的基础上，把原深度的正交不变性改进为仿射不变。
The paper shows that the revised depth is of affine invariant besides the properties owned by the original depth.
算法不仅能适应目标物体在旋转、缩放、平移变换下的不变性识别。而且能适应仿射及射影变换下的不变性识别。
The algorithm can adapt to object recognition, invariant not only under rotation? Scaling? Translation, but under affine and projective transformation.
算法不仅能适应目标物体在旋转、缩放、平移变换下的不变性识别。而且能适应仿射及射影变换下的不变性识别。
The algorithm can adapt to object recognition, invariant not only under rotation? Scaling? Translation, but under affine and projective transformation.
应用推荐