修正PCA算法能够在运行过程中自动地识别样本集之中的“劣点”,从而通过迭代计算加以适当处理来排除对运算精度的影响。
The new robust PCA algorithm can recognize the outliers in the sample set automatically and exterminate their effects to the accuracy of the PCA algorithm through proper processing to the outliers.
文中提出了两种联机手写笔画识别后处理的优化方案,第一种是基于回溯策略的后处理算法,通过回溯法修正误识的笔画; 第二种称为多候选笔画组合算法。
This paper introduces a method of on-line handwritten Chinese character stroke recognition that is suited to the needs of character glyph analysis and the practical algorithm is given.
应用推荐