Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Some problem with ctdar_measurement_tool. #4

Open
AHoou opened this issue Jun 4, 2020 · 2 comments
Open

Some problem with ctdar_measurement_tool. #4

AHoou opened this issue Jun 4, 2020 · 2 comments

Comments

@AHoou
Copy link

AHoou commented Jun 4, 2020

@cndplab-founder
Hi cndplab-founder,

  1. I am a postgraduate of BUPT in China. First, I am sorry to create a new issue in ICDAR2019_cTDaR to discuss a problem with the ctdar_measurement_tool,because I can't find the 'issue' button on the tool's page.

  2. when I tested and verified the function of ctdar_measurement_tool in table recognition task on the official website of ICDAR 2019 cTDaR, I found there are something wrong with it. General speaking, the question is that I found the result got by the tool was wrong when I increased the number of blank cells between two content cells. You missed to calculate the number of the blank cells in the evaluation tool, which is obviously not consistent with your method description. At the same time, ignoring changes in the number of blank cells isn’t a correct operation in the table recognition task. In order to ensure the correctness of my experiment, I can explain my verification process in detail.

  3. In order to explain the problem in detail, can you give me an email address?

@IceFlameWorm
Copy link

@cndplab-founder
Hi cndplab-founder,

  1. I am a postgraduate of BUPT in China. First, I am sorry to create a new issue in ICDAR2019_cTDaR to discuss a problem with the ctdar_measurement_tool,because I can't find the 'issue' button on the tool's page.
  2. when I tested and verified the function of ctdar_measurement_tool in table recognition task on the official website of ICDAR 2019 cTDaR, I found there are something wrong with it. General speaking, the question is that I found the result got by the tool was wrong when I increased the number of blank cells between two content cells. You missed to calculate the number of the blank cells in the evaluation tool, which is obviously not consistent with your method description. At the same time, ignoring changes in the number of blank cells isn’t a correct operation in the table recognition task. In order to ensure the correctness of my experiment, I can explain my verification process in detail.
  3. In order to explain the problem in detail, can you give me an email address?

Hi, Is the home page of this competition still available? I tried a few times, but it always told me that the domain name of the site can not be parsed.

@AHoou
Copy link
Author

AHoou commented Oct 22, 2020

I find that several months ago. And I think it has been stopped the service. @IceFlameWorm

@AHoou AHoou closed this as completed Oct 22, 2020
@AHoou AHoou reopened this Oct 22, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants