RChilli Parser has some limitations for the OCR Parsing like:
- OCR Parsing only works for scanned PDF files, not for imaged resume files like jpeg, gif, png, etc. We don't support PNG or any image files. The scanned resume needs to be in pdf format only, not in the image.
- The scanned file should start with the basic/personal Information. It shouldn’t be starting with any page from the middle of the resume.
- We use a third-party tool for scanned resume files known as OCR and ABBY tools. Accuracy is totally dependent upon these third-party applications. There are several limitations with OCR such as Font size, Uni-Dimensional, Case Sensitivity for Editing, Partial Text, Incorrect Document Boundaries, Small text, Blurry Copies, Mathematical formulas, Draft copies, Colored Paper and Unusual or script-type fonts, which may result in inaccurate or missing texts as it depends on a third-party application.
While parsing such CV/Resumes, we need to make sure that the resume files will contain all the relevant information according to OCR limitation so that you will get appropriate and accurate results.
You can always contact RChilli Support via creating a ticket at RChilli HelpDesk or by sending an email at firstname.lastname@example.org. The support team will enable the OCR for the Trial API Userkey to access.