未验证 提交 00a84c60 编写于 作者: L littletomatodonkey 提交者: GitHub

fix table (#1454)

上级 217b991f
......@@ -143,8 +143,9 @@ We take two scenes as examples, which are metal surface English number recogniti
After adding the above synthetic data for training, the accuracy of the recognition model is improved, which is shown in the following table:
| Scenario | Characters | Raw Data | Test Data | Only Use Raw Data</br>Recognition Accuracy | New Synthetic Data | Simultaneous Use of Synthetic Data</br>Recognition Accuracy | Index Improvement |
| -------- | ---------- | -------- | -------- | ----------- --------------- | ------------ | ---------------------| -------- |
| -------- | ---------- | -------- | -------- | -------------------------- | ------------ | ---------------------- | -------- |
| Metal surface | English and numbers | 2203 | 650 | 0.5938 | 20000 | 0.7546 | 16% |
| Random background | Korean | 5631 | 1230 | 0.3012 | 100000 | 0.5057 | 20% |
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册