通过对联机样本进行的实验证明，该分类器保持欠切分错误率在一个较低水平的同时，有效地控制了过切分的错误率。
Experiments running on real samples show that the classifier reduces the over-segmentation error rate significantly while keeping the under-segmentation error rate in a very low level.
通过对联机样本进行的实验证明，该分类器保持欠切分错误率在一个较低水平的同时，有效地控制了过切分的错误率。
Experiments running on real samples show that the classifier reduces the over-segmentation error rate significantly while keeping the under-segmentation error rate in a very low level.
应用推荐