建立仿射不变的形状相似性度量是模式识别、计算机视觉和图象理解领域中的基本问题之一。
Establishing affine invariant similarity measure of shapes is one of the basic problems in pattern recognition, computer vision and image understanding domains.
提出了在图象匹配中使用的一些新的仿射透视近似投影不变量。
This paper proposes some new affine-perspective approximate invariants that are used in image matching.
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.
应用推荐