mirrors/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-06-03 21:53:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix table (#1454)

Browse Source
This commit is contained in:
littletomatodonkey 2020-12-16 00:59:32 +08:00 committed by GitHub
parent 217b991f05
commit 00a84c605b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
StyleText/README.md
View File

@ -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: 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 | | 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% | | Metal surface | English and numbers | 2203 | 650 | 0.5938 | 20000 | 0.7546 | 16% |
| Random background | Korean | 5631 | 1230 | 0.3012 | 100000 | 0.5057 | 20% | | Random background | Korean | 5631 | 1230 | 0.3012 | 100000 | 0.5057 | 20% |