Hi everyone, I want to scrape the paragraph from this image file attached below, as the image contains watermark, the OCR is scraping the watermark as well. Is there any way it can neglect the watermark, I have tried screen, scan profile in tesseract OCR as well.
plz help
thanks in advance
No. All OCR engines will try to get any and all text they can find.
You can try removing the watermark text after you have the OCR’d text.
How can i remove watermark using uipath?
Taking your example, the watermark is only the word ‘draft’ so it might be possible to simply remove the word draft from your text with an assign activity like so:
newtext = ocrtext.replace("draft","")
ashokkarale
Anil_G
Yoichi
yangyq10
postwick
chandreshsinh.jadeja
aravindbalineni123
Parvathy
aya
PRASHANT_GABHANE