《Table 1 Comparison of correct categorization rates using CNN, SVM and Ada Boost》

  提示：宽带有限、当前游客访问压缩模式

本系列图表出处文件名：随高清版一同展现

《Semantic categorization of indoor places using CNN for mobile robot exploration》

1. 获取 高清版本忘记账户？点击这里登录

1. 下载图表忘记账户？点击这里登录

In this research，the CNN-based classifier is trained by using 320 training examples from the dataset，i.e.each training set contains always eight categories and each category contains 40 panoramic images，and the rest of data are used for test experiments.The test experiments are done repeatedly 20 times，and the categorization results of the three methods with respect to their average correct categorization rate for each category are summarized in Table 1，in which the best results are typed in bold.