Is it possible to parse Scanned files using OCR?

Yes, it is possible to parse scanned files. RChilli is providing an add-on facility, OCR to parse scanned resumes.

A scanned document is difficult to convert, as it requires a third-party OCR tool. The accuracy of the results depends upon the third-party application. As every resume comes to RChilli API first, RChilli will decide whether it is genuine, junk data, Scanned, or non-scanned one. 

1.  If the resume is non-scanned, not junked, etc., as it is a simple resume, it will be parsed by the RChilli PDF converter and not forwarded to the OCR converter; only RChilli credit will be counted.
2. On the other side, if a resume is scanned, the RChilli PDF converter will pass it to the OCR converter and be processed by the OCR converter. OCR converts the scanned resume content to text and is returned to RChilli, and further RChilli API will parse it to JSON response. Then one credit of RChilli is counted, and in the same way, the number of scanned pages of OCR will be charged.
3. If the document is partially scanned, it is treated as a normal document and it is not converted through an OCR converter.
4. Last, if a resume is a junk one, it will be checked by RChilli first and recognized as junk. In this case, Resume will be considered failed, not forwarded to the OCR converter, So neither RChilli nor the converter will be charged for this.

Note:- Due to the third-party dependency and text file conversion, it might take a little time while parsing & processing files.

If you have any questions, drop us an email at support@rchilli.com.