Hello,

We are processing a lot of UK & European Driving Licences through the API. We're having problems with the various layouts and some of the weird character shapes for "A" and "0" specifically.

Would it be possible to have a simple API call, similar to the one you have already for processBusinessCard, that returns all the fields in ready-made fields?

e.g. On the licence, the last name field is prefixed with "1{dot}{space}", but sometimes we miss this if the 1 looks like an l, or the dot looks like a comma.

e.g. the expiry date is hidden in a line prefixed with "4b{dot}{space}".

I've tried and failed to use processFields to pick out these values as the scanned images we are receiving are not in a fixed size, format or orientation so I can't specify the regions.

Thanks,

asked 14 Jun '13, 18:04

evergreen's gravatar image

evergreen
914

It would be great to show sample image

(14 Jun '13, 20:20) Andrey Isaev ♦♦

Plenty here for the UK Licences:

google.co.uk/search?hl=en&source=lnms&sa=X&tbm=isch&q=uk+driving+licence&oq=uk+driving+licence

and then try "european driving licence" to see how similar the layout is for those other countries.

It's the pink card part that we're scanning. Not interested in the photo, just the text.

More examples: http://scrapmetalsoftware.co/cms/clients/client-3-dfadfwerr1/s12532/ident20701big.jpg http://scrapmetalsoftware.co/cms/clients/client-3-dfadfwerr1/s12621/ident10475big.jpg http://scrapmetalsoftware.co/cms/clients/client-3-dfadfwerr1/s45681/ident13237big.jpg

(14 Jun '13, 20:53) evergreen

Thank you for the images!

Now you can try to use the ProcessImage method with the textExtraction or fieldLevelRecognition profile (we recommend to test which one is better for this task).

To get the field values, you can export the recognized words with its coordinates to an xml file and then extract the necessary information on your side. To get the initial word coordinates, you have to turn off the automatic geometric correction: set imageSource=scanner, correctSkew=false (it is possible if your images are not too distorted).

Also we are consulting with the product analyst if the driving licenses recognition could be simplified in the future and will come back soon.

link

answered 14 Jun '13, 23:15

Anastasia%20Galimova's gravatar image

Anastasia Ga... ♦♦
790112

The analyst said that a special API for the driving licenses recognition is not included in our plans for the nearest future. If it is important to you, you can purchase it (in this case, please contact ABBYY Europe office at engine_eu@abbyy.com).

(17 Jun '13, 13:31) Anastasia Ga... ♦♦
Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here

By RSS:

Answers

Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "title")
  • image?![alt text](/path/img.jpg "title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported

Tags:

×160
×20

Asked: 14 Jun '13, 18:04

Seen: 1,562 times

Last updated: 17 Jun '13, 13:31

© 2016 ABBYY. All rights Reserved. www.ABBYY.com | Privacy Policy | Legal