1) registration probability
配准概率
1.
The experiments show that the method not only can keep high registration probability and greatly improve the registration speed,but also can restrain noise powerfully.
通过实验验证,这种方法在保持高的配准概率的前提下,大大地提高了配准速率,降低了算法复杂度,不仅抗噪能力强,而且仅仅只有和差运算,也易于硬件实现。
2) probability criterion
概率准则
1.
Portfolio investment model with probability criterion;
组合证券投资的概率准则模型
2.
Portfolio model of short selling with probability criterion;
允许卖空情况下证券投资组合的概率准则模型
3.
Stochastic simulation based genetic algorithm for solving portfolio problem with probability criterion;
基于遗传算法的概率准则组合证券模拟求解
3) probability partition
概率配分
1.
In order to extract anatomical feature of several tissues from CT image and solve the contradiction between the improvement of the searching speed and instability of the results,a method for image segmentation using probability partition and maximum fuzzy entropy is proposed.
为了找到分割灰度图象的最佳阈值,根据模糊聚类和概率配分之间的关系,以及模糊熵有最大值的必要条件,从而得到各类的概率配分,因此在搜索阈值组合时,先搜索满足各类概率配分的阈值,然后从这些阈值中搜索使模糊熵最大的阈值。
4) matching probability
匹配概率
1.
In the class,the matching is based on matching probability.
结果实现了分形图像定义域块的自动分类,在匹配时通过类内搜索代替全局搜索;在类内匹配时进行基于匹配概率搜索。
2.
The advantage of the method is higher matching probability,and the disadvantage is slower matching velocity.
目前图像匹配的方法主要有两类:一种是基于灰度的图像匹配,这种方法匹配概率高,但速度较慢;另一类是基于特征的图像匹配,这种方法匹配速度快,但匹配概率不高。
6) match probability
匹配概率
1.
This paper establishes the Bernoulli statistical model of match simulation experiments,estimates match probability calculation formula of image matching algorithm based on estimation method.
建立了匹配仿真试验的贝努里(Bernoulli)统计模型,根据数字特征法,估计了基于序列图像匹配算法的匹配概率计算公式,证明了该模型的无偏性,并进行了精度分析。
2.
Firstly, abbreviations are identified according to the ruler databases, then the features are used of such as match probability and mutually infor- mation probability to restore abbreviations.
利用规则对初分词后形成的散串进行缩略语的识别,然后利用缩略语相对稳定的抽取规律这一特性,通过统计生成缩略语字对应原语言词的词典,利用匹配概率和共现概率进行缩略语对应原语言的还原。
补充资料：几何配准
几何配准 geometric registration
将不同时间、不同波段、不同遥感器系统所获得的同一地区的图像(数据)，经几何变换使同名像点在位置上和方位上完全叠合的操作。
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