Hello,
The main readme of this project makes this statement :
Here is an example image. SwiftOCR has no problem recognizing it. If you try to recognize the same image using Tesseract the output is 'LABMENSW' ?!?!?.
That statement is not correct.
With Tesseract version 4 and higher, the output is perfect and the image does not require any preprocessing. Speaking from experience, Tesseract can successfully handle images that have far worse contrast too.
Hello,
The main readme of this project makes this statement :
That statement is not correct.
With Tesseract version 4 and higher, the output is perfect and the image does not require any preprocessing. Speaking from experience, Tesseract can successfully handle images that have far worse contrast too.