Jump to content

Recommended Posts

Posted

I have a Thai document I have scanned to PDF that I want in English.

 

If I point my Google Translator Android Camera phone at the PDF it translates to English on my phone screen at the bits I point to, but that is not convenient as the screen is small to see anything clearly and I want to whole PDF document converted to English anyway. However the translate seems to output English OK.

 

If I go on a PC to https://translate.google.com using the same PDF selected using the Documents tab thus using no camera and hoping to see the full PDF translated on my PC screen I just get garbage out from Google? 

 

How come? What is a good way to convert a PDF of scanned Thai document to English? Doesn't have to be exact, just give idea of the meaning is OK?

Posted (edited)

Typically you'd first OCR the picture/image pdf, quickly proof that the thai was mostly recognized, then submit the thai text version for conversion. Note: this process works 'ok' for letter documents and not at all for free-form infographic posters where the text is everywhere.

 

https://www.google.com/search?q=ocr+pdf+to+thai+text+online 

https://www.sejda.com/th/ocr-pdf

 

EDIT:  You can also try uploading the .pdf or an image to Google Drive and it will try to OCR the doc for you.

 

https://support.google.com/drive/answer/176692?co=GENIE.Platform%3DDesktop&hl=en&oco=1

Edited by RichCor
  • Like 1
Posted
6 minutes ago, RichCor said:

Typically you'd first OCR the picture/image pdf, quickly proof that the thai was mostly recognized, then submit the thai text version for conversion. Note: this process works 'ok' for letter documents and not at all for free-form infographic posters where the text is everywhere.

 

https://www.google.com/search?q=ocr+pdf+to+thai+text+online 

Yes, I think I need to get an OCR to Thai text from the image format. Will do a search for some offline options. Thanks.

 

Strange the Google Translate on a phone camera does it automatically yet their web site translator does not.

Posted
11 hours ago, RichCor said:

You can also try uploading the .pdf or an image to Google Drive and it will try to OCR the doc for you.

Interesting. I tried it and the result was the same as https://translate.google.com with mostly rubbish output by OCR and a few English text characters. I'm kind of not surprised as the original PDF scan image is not exactly clear text so must be hard for OCR to decipher. If I tried it with Thai text typed into a PDF doc it can OCR that PDF OK.

 

Nevertheless the android phone app Google Translate by camera seems to work where my uploaded to Google PDF doesn't somehow, just pointing the camera and displaying Thai-English real time on the phone screen. It's a pity the phone screen output is harder and messier to capture and only suited to just quickly glancing at.

Posted

Have you tried using your phone to take a clear image of the document (or sections of it), then using the Google PHOTOS app 'lens' option (the photo sight/target icon) and have it recognize the Thai Text? 

 

Google LENS has options to ocr/translate, ocr text, auto, shopping, places, dining ...i'd suggest using the selecting the second "text" icon and then COPY TEXT or COPY TO COMPUTER (if your computer is signed into the same google account as the phone).

 

Example: I used my phone to take a picture of some previously photocopied Thai Text, then opened Google PHOTOS on my phone and selected the target/sight icon.

 

Screenshot.thumb.jpg.944243b33339917138ab09e511fe5a62.jpg

 

 

 

 

  • Like 1
  • Thanks 1
Posted (edited)
5 hours ago, RichCor said:

Google LENS has options to ocr/translate, ocr text, auto, shopping, places, dining ...i'd suggest using the selecting the second "text" icon and then COPY TEXT or COPY TO COMPUTER (if your computer is signed into the same google account as the phone).

That's awesome and it worked on my document. I never knew about this Google LENS, previously I used the camera function on the Google Translate phone app, but thanks so much as LENS really works. I used COPY to computer and it comes as clear Thai text and not garbage OCR,  then I can paste that into Google Translator immediately.

This will help me quickly translate Thai documents I receive - I can read some Thai but this will speed things up no end.

 

Great tip and thanks so much.

Edited by WorriedNoodle
Posted
19 hours ago, WorriedNoodle said:

It's a pity the phone screen output is harder and messier to capture and only suited to just quickly glancing at.

A photo of the screen is useless for OCER purposes. Instead, take a so-called screenshot, the procedure for which depends on the device you are using.

Posted
7 hours ago, Puccini said:

A photo of the screen is useless for OCER purposes. Instead, take a so-called screenshot, the procedure for which depends on the device you are using.

The procedure I have adopted (thanks to @RichCor) is I to point the phone Camera using Android Google LENS app at a Thai language paper document (or it could be a scan of the document on a clear PC screen) and choose the copy text to a computer on the phone screen option of LENS. This OCR copies THAI text very well and I can paste that into anything, including a translator on a PC. I don't know how else to do it.

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Recently Browsing   0 members

    • No registered users viewing this page.



×
×
  • Create New...