相关分析主要是计算相关系数，模糊识别主要是计算监测点波形的模糊隶属度。
Correlation analysis is to calculate the correlation coefficient mainly, and vague identification is to calculate the vague subordinate degree of waveform at monitored point.
研究了异常点对相关系数的影响。
The influence of singular point on correlation coefficient is researched.
利用相关系数在真实匹配点附近的统计特性，通过对相关系数进行曲线拟合，根据其一阶导数确定最大相关系数所在的位置，快速得到亚像素匹配点。
By using the statistic properties of the correlation coefficient, a curve correlation coefficient is calculated, and then the matching point is obtained through evaluating it's derivative function.
在立体匹配时，将灰度相关系数小于最大灰度相关系数一定范围内的特征点作为灰度相关复峰初始匹配特征点集合。
During stereo matching, the feature points whose correlation coefficients are within certain range less than the maximal coefficient can be taken as an original matching feature point set.
计算相关系数时，每次增加参与匹配的点后，首先只对新增的点进行计算，然后与原有的相关系数进行组合，得到新的相关系数。
When calculating the correlation coefficient, we just calculate with the new points, and then merge it with the original correlation coefficient to get a new correlation coefficient.
计算相关系数时，每次增加参与匹配的点后，首先只对新增的点进行计算，然后与原有的相关系数进行组合，得到新的相关系数。
When calculating the correlation coefficient, we just calculated with the new points, and then merged it with the original correlation coefficient to get a new correlation coefficient.
计算相关系数时，每次增加参与匹配的点后，首先只对新增的点进行计算，然后与原有的相关系数进行组合，得到新的相关系数。
When calculating the correlation coefficient, we just calculated with the new points, and then merged it with the original correlation coefficient to get a new correlation coefficient.
应用推荐