Assigned
Status Update
No update yet.
Comments
lj...@gmail.com
Hello,
To assist us in conducting thorough investigation, we kindly request your cooperation in providing the following information regarding the reported issue:
- Has this scenario ever worked as expected in the past?
- Do you see this issue constantly or intermittently ?
- If this issue is seen intermittently, then how often do you observe this issue ? Is there any specific scenario or time at which this issue is observed ?
- To help us understand the issue better, please provide detailed steps to reliably reproduce the problem.
- It would be greatly helpful if you could attach screenshots of the output related to this issue.
Your cooperation in providing these details will enable us to dive deeper into the matter and work towards a prompt resolution. We appreciate your assistance and look forward to resolving this issue for you.
Thank you for your understanding and cooperation.
lj...@gmail.com
Hello,
Thank you for reaching out. Here is the information requested regarding the reported issue:
In response to the first point, I previously conducted an uptraining with approximately twenty bank statements, and this issue did not occur.
For the second point, I have attempted the uptraining three times, and the same error appeared each time.
To reproduce the issue: I labeled 76 bank statements, dividing them as follows—59 in the training dataset and 17 in the test dataset. I also modified the label schema by deactivating the following labels: account_types, bank_address, bank_name, client_address, and client_name. Additionally, I created a new label for rib (bank account identifier). I then proceeded to uptrain a new version, and the issue arises during this process.
I hope this information helps clarify the situation. Please let me know if you need any further details.
Thank you for your assistance in resolving this matter.
Thank you for reaching out. Here is the information requested regarding the reported issue:
In response to the first point, I previously conducted an uptraining with approximately twenty bank statements, and this issue did not occur.
For the second point, I have attempted the uptraining three times, and the same error appeared each time.
To reproduce the issue: I labeled 76 bank statements, dividing them as follows—59 in the training dataset and 17 in the test dataset. I also modified the label schema by deactivating the following labels: account_types, bank_address, bank_name, client_address, and client_name. Additionally, I created a new label for rib (bank account identifier). I then proceeded to uptrain a new version, and the issue arises during this process.
I hope this information helps clarify the situation. Please let me know if you need any further details.
Thank you for your assistance in resolving this matter.
Description
Please provide as much information as possible. At least, this should include a description of your issue and steps to reproduce the problem. If possible please provide a summary of what steps or workarounds you have already tried, and any docs or articles you found (un)helpful.
Problem you have encountered:
Some numbers in the Korean text cannot be recognized; some characters in the Korean text are mistakenly identified as numbers; some spaces in the Korean text cannot be recognized.
What you expected to happen:
I found that Google Drive's OCR, Document OCR, and Cloud Vision OCR all have this problem. Please improve those three OCRs to fix this problem.
Steps to reproduce:
All error sample images are included in the zip file.
All images include two files, error samples and original images, and the locations of all error samples have been labeled.
Please ask the engineering team to use my original images to reproduce the errors. I have performed OCR on the same image multiple times, and these errors always occur.
CPU version ID is: <pretrained-ocr-v1.2-2022-11-10>