Does Relativity perform OCR on PDF files during processing?

Relativity does perform Optical Character Recognition (OCR) on PDF files during processing. The primary purpose of OCR is to convert different types of documents, including scanned documents and images, into editable and searchable data. In the context of PDFs, this functionality allows Relativity to recognize text within the files, which is crucial for effective indexing and searching.

When PDFs are processed in Relativity, any text that is not already selectable—such as text contained within scanned images—can be made searchable through this OCR process. This enhances the ability to review and analyze document contents, making it easier to identify relevant information during legal discovery.

While there are options that reference OCR being applied only under certain circumstances or only to images, the system's capability includes a more comprehensive application of OCR across PDF files to ensure thorough processing. The inclusion of OCR for all PDF files aligns with the platform's goal of maximizing the usability of document data.