Coordinates of textField when using a mobile phone camera

  • Last Post 10 April 2012
  • Topic Is Solved
dale posted this 09 April 2012

Hi, thanks for this great service. I have a basic Android example working but wonder if you could help suggest a way forward for this usage case. I want to use the mobile phone camera to take a photograph of a form and then use the region parameter of the processTextField call to recognise some handwritten / checkbox data. What I can't figure out is how to accurately provide the region parameters as photographing the form always puts the text-fields in slightly different positions. Your thoughts / help would be appreciated.

Order By: Standard | Newest | Votes
Nikolay_Kh posted this 09 April 2012

What you describe is a step further from OCR and closer to data capture scenarios. We are planning to implement layout training and document classification features to ABBYY Cloud OCR SDK, but i can't say anything about the timing right now. Meanwhile, i've got two suggestions on solving your task:

  1. Do a full OCR for your image (or its piece) and look for the document specific text (form ID code, form title, specific question, etc.). If you use exportFormat=xml you'll be able to retrieve coordinates of that text and pass relative coordinates respectively. That's one of the high-level approaches used in the technologies from the product in the next list item.

  2. Alternatively, have a look at ABBYY Mobile Data Capture Solution, it's a non-cloud based mobile data capture SDK designed to solve the task you describe.

I beleive both approaches would do the job for you, i suggest you use the first approach, as it would be easier to implement and if you feel that you need more sophisticated data capture functionality - go for ABBYY Mobile Data Capture Solution.

Nikolay_Kh posted this 10 April 2012

@dale, i've made the edit with some additional suggestions, please let me know if you have any more questions.