Data Extraction from Image

hi everyone,
I want to extract the data of some images ,and only some specific fields. i used tesseract ocr engine but
it is not extracting some specific data like invoice no,customer id etc may be because of the small font .i am attaching my image for the reference.I am new to UI path and I would like to know How to use OCR with Image so Could anyone send me a sample or steps to do it

1 Like

Hi @nahma_salim
As I can see your invoice, I dont think its, your invoice number is too small to ocr that even computer printed

Can you tell us the issue with web you try to extract like invoice number alone and what happens

Try the several ocr method,

Hi @nahma_salim

You need to send hotkey to zoom in your image first.

1.Start Process to open your image

2.Send Hot key to Zoom in your image
3.Send Hot key to Move to your area that your want scraping
4.Scraping data (If you cannot get data, please try to adjust scale)

5.Remove blank spaces
(sample command: Invoice_no = Invoice_no.Replace(" ", [String].Empty))

Check Output:

For guidelines
Sample screen (1.7 MB)

I hope it will be useful to you :blush:

1 Like

Thank you for your reply @Maneesha_de_silva
I have used microsoft ocr engine to extract the text it is extracting most of the data from the image.
Thank you very much

1 Like

You are always welcome :+1: