Repository navigation
Replies: 2 comments 1 reply
|
Do you mean performance as in speed, or performance as in recognition accuracy? |
1 reply
|
There aren't any proper accuracy benchmarks against well known datasets - help creating evaluation tools for this is welcome. In general it depends on the input image. Tesseract can be more accurate on "clean" document images, but Ocrs can handle a wider range of input images (varying text styles, varying backgrounds, light text on dark backgrounds etc.). Tesseract has models for a variety of languages, Ocrs only has one model trained predominantly on English. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Have you created some performance checks or tests to observe its performance when compared against tesseract ?
All reactions