A novel feature fusion algorithm based on KCCA is established.

提出一种新的KCCA特征融合算法。

youdao

For the best feature, we also use the classifier based on KCCA to reclassify it.

对检测率最高的特征，我们用基于核典型相关分析的分类器重新分类。

youdao

The experimental work shows that the KCCA based classier outperform SVM, especially when the embedding rate is low.

实验结果表明，其检测率超过支撑向量机，在嵌入量低时，效果尤为明显。

youdao