1) Three-order affine invariant moments
3阶仿射不变矩
2) affine moment invariants
仿射不变矩
1.
Auto-recognition of shaft orbits using affine moment invariants;
基于仿射不变矩的轴心轨迹自动识别方法
2.
In the 3D object recognition system,this paper presents to combine the lower order of Hu’s moment invariants and affine moment invariants together as features of 3D objects,then these features are presented to the modified BP neural network for 3D object recognition.
在三维物体识别系统中,提出将三维物体的Hu不变矩和仿射不变矩两者的低阶矩组合作为三维物体的特征,结合改进的BP神经网络应用于三维物体的分类识别。
3) affine invariant moment
仿射不变矩
1.
It computes the affine invariant moments of SER and measures the Euclid-distance between the region and another.
在此基础上计算了区域的仿射不变矩及衡量对应区域的欧氏距离。
2.
A new combined invariant moment is presented in this paper according to the characteristics of NMI and affine invariant moments proposed by Jan Flusser with their application conditions.
根据NMI特征和Jan Flusser提出的仿射不变矩的特点及各自的适用条件,提出了一种组合不变矩。
3.
Secondly,affine invariant moment is used as the invariable characteristic for overcoming the shortcoming that it can not recognize the affine deformation target.
该算法首先利用改进后的瞬时差分算法对序列图像中的运动物体进行检测和定位,提高检测与识别的实时性;其次,采用仿射不变矩作为提取目标时的不变特征,从而克服不能有效检测与识别时发生仿射形变目标的缺点。
4) combined blur-affine invariants(CBAIs)
模糊-仿射联合不变矩
1.
In order to cope with the degradation,combined blur-affine invariants(CBAIs) were adopted to recognize the traffic sign symbols without any restorations based on many computations.
该算法在处理图像退化问题时,采用模糊-仿射联合不变矩直接提取图像的特征,从而避免了需要较大计算量的图像复原处理过程。
5) affine invariance
仿射不变
1.
The affine invariance is a challenging problem in pattern recognition.
仿射不变模式识别是模式识别问题中的一个难点问题,本文提出了一种基于全局特征的仿射不变特征提取方法。
6) affine invariant
仿射不变
1.
For the purpose of wide baseline stereo image matching, a filter strategy of affine invariant feature based on information content and spatial distribution constraints is put forward.
针对宽基线影像匹配问题,提出基于信息量和空间分布均衡性双重约束的多层次特征筛选方法,并在此基础上探讨集成该特征筛选方法、MSER(Maximally Stable Extremal Region detector)、SIFT(Scale Invariant Scale Transformation)的特征提取算法,以达到提取高质量(高信息量、空间分布均衡、高重复率)仿射不变特征的目的。
2.
The paper shows that the revised depth is of affine invariant besides the properties owned by the original depth.
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。
3.
In this paper,affine invariant points of original and probe image are computed to estimate the geometric parameters.
本文采用仿射不变特征点匹配方法估计图像所经历的几何变换参数,其中特征点匹配通过遗传算法实现。
补充资料：仿射
仿射
affinity
仿射!确nity;呻中Ifu盯er] 仿射变换陌币ne transfo瓜atlon)的简称定义为非退化线性代换 二A派丰“
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条