Documents scanned in differente resolutions

  • Last Post 29 January 2014
Francisco Tirado posted this 29 January 2014

I want to recognize a couple of fields in a document but the documents (although the same form) Might be scanned in different resolutions or maybe skewed.. Does the cloud recognition engine make corrections?

Anastasia Galimova posted this 29 January 2014

No, unfortunately it does not.

If the fields you need contain the common (not handprinted) text only, you can recognize full page, export all the text with its coordinates to xml and find the text you need.

If the fields you need contain handprinted text (or checkmarks - in these cases it is necessary to specify exact fields coordinates before recognition):

You can define field coordinates using coordinates of another object (it could be symbols like "@", the best results are achieved when it is a barcode or a couple of words; to let short text fragments be recognized, use the textExtraction profile).

So, the scenario in this case is:

  1. Recognize full page using the processImage method, export the result to xml.

  2. Get the coordinates of the object you know from this xml.

  3. Using this coordinates calculate the coordinates of the field you need.

  4. Recognize the necessary field using field-level recognition.

It will be billed as one page (you can recognize fields on an image that was already recognized for free).