Optical Character Recognition (OCR) is technology that aids in converting paper based documents, images and large volume repositories into electronically searchable and archival data. OCR can work with both hard copy data and digital information helping reviewers and teams boost visibility and control over their data.
Through using OCR best practices and early implementation reviewers are able to handle and scale growing data sets. Reviewers are able to more effectively identify the relevant documents for their case boosting litigation readiness and eliminating redundant or non essential manual review. As a result you save money and time while boosting your discovery cycle time.
OCR & large data repositories go hand in hand, through structuring your large data sets. You in turn create reusable environments that can be used across multiple matters.
Advanced OCR technologies can now work with various different fonts and custom typefaces and increasingly more are able to convert handwritten text. Although not 100% accurate industry confidence has OCR between 80-99% according to FD.org