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

Inverse text problem found by Viewerdebugging #641

Closed
Tangzy7 opened this issue Jan 6, 2017 · 2 comments
Closed

Inverse text problem found by Viewerdebugging #641

Tangzy7 opened this issue Jan 6, 2017 · 2 comments
Labels

Comments

@Tangzy7
Copy link

Tangzy7 commented Jan 6, 2017

I used Viewerdebugging and used "Recog Blob" to classify each Blob. I just found that some blobs are input as white-on-black text. However,some are black-on-white text. See the 2 images. The white-on-black text cannot be recognized correctly
wechatimg11

wechatimg12

@amitdo
Copy link
Collaborator

amitdo commented Jan 6, 2017

It looks like you are trying to OCR vertical (Chinese / Japanese) text.
#627 (comment)

@zdenop
Copy link
Contributor

zdenop commented Sep 17, 2021

This is a know behavior - for tesseract 4 and above you need to use black on white (or dark on light) images
https://github.com/tesseract-ocr/tessdoc/blob/main/ImproveQuality.md#inverting-images

@zdenop zdenop closed this as completed Sep 17, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants