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.

Sign up for GitHub

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

Jump to bottom

Feature/text recognition #8

Merged
merged 3 commits into from
May 21, 2019
Merged

Feature/text recognition #8

merged 3 commits into from
May 21, 2019

Conversation

markusressel
Copy link
Collaborator

@markusressel markusressel commented May 20, 2019 •
edited
Loading

This PR allows text recognition on images.
There are two implementations:

  • Google Vision API
    • pretty accurate most of the time even in difficult conditions
    • not free for unlimited amounts of requests
  • Tesseract
    • needs system level packages installed to be functional
    • hit or miss without proper preprocessing of the image
    • on device and free

Since there is no persistence yet there is no use for text recognition in the actual bot code so neither of the implementations in this PR are used. This is easy to add at a later stage though.

I wanted to play around with this topic so I just implemented it, it would be obviously much better though if the original service would provide the exact text (or the images were generated from this bot itself).

This supports #1

@ekeih ekeih merged commit a83a745 into ekeih:master May 21, 2019
@markusressel markusressel deleted the feature/text_recognition branch May 21, 2019 18:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@markusressel @ekeih