Pdf get ocr text format changing

hii guys i’m just working on get ocr text activity,though i’m getting the output the format of the text has been changing say for example if the date is 21 sep 2016 it is extracting as 215139;: 2016 even i tried with get full text but it is showing null value plz help me out from this .thank you

@venkatmalla6

Which OCR engine are you using ? And also try with different OCR engines. Change the scale value and try.

Have you tried with Computer Vision activities.

i’m using tesseract ocr and i tried with computer vision but it is saying not find the element.

1 Like

@venkatmalla6

What kind of application it is ?

Kindly try once with CV activities


Cheers @venkatmalla6

Try with Google OCR once
Cheers @venkatmalla6

@Palaniyappan @lakshman teseract ocr is only available in my package and it worked with increase of scale but for some texts even though i’m changed the scale it is not upto accurate

@venkatmalla6

Is document is hand written ?

Is the document data is clearly visible or not ?

@lakshman no it is pdf and it is visible clearly