Forms Processing

Forms processing is performed by electronically extracting data from a document through Optical Character Recognition technology, manual data capture or a combination of both.  We utilize a number of different OCR conversion packages, each of which has its own strengths for certain types of documents. DX tailors data extraction and capture to the specific requirements of a project. We carefully analyze client needs and test different alternatives before recommending the conversion process that best meets our client’s requests. The primary objective is to extract as much data as possible with our OCR tools to minimize the number of images that require manual data entry and hence cost.

In general, for an OCR process to be effective it needs to recognize around 75% to 80% of the targeted data fields. Less than such accuracy rate results in an unproductive task for a key entry operator since there would be a need to correct the wrong character in more than one set of five capture fields, to the point that is faster to re-key the complete data field.  

FAQ

>> How do I know if OCR is a feasible option to extract data from my documents?

The only way to find out is by evaluating the source document and running a readability test. However, variable such as: standard forms, computer printed documents, physical condition of documents and legibility, will determine whether OCR is a viable option or not.

>>  What is the main benefit of using OCR?

Reduces data capture cost and improves the quality of the data. 

>>  What if I need to add or eliminate a data field?

Just let us know the specific field (s) and time of implementation and we would make the necessary modifications to reflect your new requirements.

>>  What if the form changes or is completely redesigned?

In either case, DX can adapt to the changes provided reasonable time is given for modifications and testing.