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

Fixed image processing bugs #20

Merged
merged 9 commits into from
Dec 29, 2020
Merged

Conversation

ellbosch
Copy link
Contributor

@ellbosch ellbosch commented Dec 14, 2020

This PR fixes bugs pertaining to the camera view:

  • Fixed image rotation issue, ensuring image is now in correct orientation before running inference
  • Fixed issue where images were slightly distorted before getting processed
  • Fixed issue where front-facing camera inverted view on x-axis
  • Moved image processing task to background thread
  • Changed screenshot to save the image used before inference rather than the screenshot of the entire view
  • Stopped sending image processing for inference if no image found

Inference is now much more accurate—before we'd see incorrect results due to orientation and cropping issues, but these are now fixed with this PR.

Tagging #17

@ellbosch ellbosch marked this pull request as ready for review December 15, 2020 05:16
@ellbosch ellbosch merged commit 910efff into u/elbosc/main Dec 29, 2020
@ellbosch ellbosch deleted the u/elbosc/56/camera-improvements branch December 29, 2020 20:40
ellbosch pushed a commit that referenced this pull request Feb 13, 2021
* Refactors to adhere to MVVM architecture (#14, #21)
* Adds CI pipeline (#19)
* Fixes bugs (#20)
* README updates
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

Successfully merging this pull request may close these issues.

1 participant