I am having the following image and trying to extract the text using pytesseract. But, it always returns some unknown character.
Image
This is the code I am using:
import pytesseract as pt
from PIL import Image
#Converting image to text
img = Image.open('frame-1ROI_2.png')
extracted = pt.image_to_string(img)
print(extracted)
print(type(extracted))
This is the output
If I use this online text extraction tool, it does extract the text and returns the correct text.
Update 1
I have made this code change and the result is still the same.
img = img.convert("L")
img = img.filter(ImageFilter.SMOOTH_MORE)
The image now looks like this:
I have also tried this method but the output is still the same.
