I recently completed a large legacy DM (Trust Imaging Joshua) conversion project, transferring nearly 200,000 PDF files of scanned images (~2 million pages) to Laserfiche. We OCR’d all of the PDF files outside of Laserfiche using Nuance PowerPDF and its batch OCR processor, and then imported the PDFs into Laserfiche.
Some of the images in the files were fairly complex, and we ran into certain types of images that would cause either incredibly slow processing (like 10 minutes per page) or complete OCR failures with the Nuance Omnipage OCR engine. Nuance support looked at samples of our "trouble" files and over time provided numerous hotfixes that have managed to solve nearly all of the slow processing/crash issues.
With the backlog complete, we’re about to start using Laserfiche to bring in new scanning/OCR jobs, and seeing how Laserfiche uses the same Nuance OCR technology, I’m wondering how often you update the engine and when I might see those same hotfixes show up in the Laserfiche release of Omnipage?
Thanks,
Geoff