Since 3.0 release DocScanner for iPhone has had a limited text recognition feature that made documents searchable. We ended up limiting the feature since the quality of the OCR was limited. Now we have found set of workarounds and the next release of DocScanner is going to have full OCR support.
Obviously the OCR will make some errors. Quality of OCR is quite good with the 3GS. With 3G and older it will make more errors. Known limitations at the moment include:
- No support for copy & paste (expect to have it soon)
- Poor quality with 3G and older
- OCR supports only Latin alhpabets
As you can see in the attached PDF the recognized text is behind the the scanned image. Therefore the document is always good to print and read, even if the OCR has made errors. Try to select and copy text to see how OCR has done the job.
In near future we will make our best to include support for Japanese and improve user interface to make it fast to use DocScanner for capturing text from the real world to be attached to emails, SMS messages and anywhere with copy & paste. Please find the attached PDF that demonstrates how it works with A4 document scanned with 3GS.
either scanning handwritten notes or bills for archiving.
folders would be nice – manual rotation (on iPhone) is really missing (horizontally taken pictures are often wrong orientated)
Hi,
Manual rotation is there, but the ui is not good. After scanning you can make circle with you finger and the document rotates. Next release 3.0.3 is out in few days and after that you can use two-finger gesture (similar to Preview.app on Mac) to rotate documents. Currently we do not have plans for handwrite recognition (only OCR), however Evernote does great job wit that.
I’m blind, and would use an iPhone with OCR to read the mail, travel timetables, possibly street signs,, ingredients on food packages, leaflets that come with medication…….. maybe even some short stories from a book.
All of this would be great for preserving my independence and reucing my call on public services.
The iPhone is particularly good for this because of the built-in text-to-speech.
I get the DocScanner to use the OCR but I can’t find it ?
Could you advise me how can I use it?
Thanks,
Atef
The OCR is done when you run the “Spooler”. After this all exported PDFs have the OCR data and you can copy the text with PDF reader on your computer.
Hope this helps.