Back to All Posts

Grooper Continues to Reinvent Document and Data Capture with Version 2.7

OKLAHOMA CITY, AUG. 8, 2018 – Grooper, the world’s leading software platform for discovering data and transforming it into actionable information, packs even more power in its latest release, Grooper 2.7. The newest capabilities further simplify document and data capture workstreams, enhance extraction accuracy, and support multi-language processing.

“Grooper was born out of the need to overcome the limitations of traditional document and data capture platforms, and each new release further propels Grooper into a league of its own,” said Dan Rotelli, CEO of Grooper, LLC. “Organizations across diverse industries – financial services, government, oil and gas, education, healthcare – continue to discover the Grooper difference.”

New Algorithms Improve Capture Accuracy

Grooper 2.7 features an entire suite of modern image processing algorithms that more effectively clean up document images, resulting in better OCR results and faster processing speeds. For example, white text on a colored or shaded background is automatically reversed to black text on a white background, which improves the accuracy of data captured from headers and tables.

Organizations that extract data from contracts, land records, mortgage documents, invoices, etc., will benefit from advanced line detection and removal tools in Grooper 2.7. By detecting lines and masking them, without harming the text in and around the lines, Grooper non-destructively provides cleaner images for OCR. Other line removal tools erase lines in a vertical or horizontal swath, damaging nearby characters and leaving behind artifacts that decrease OCR accuracy.

New algorithms also ease table extraction tasks and eliminate the need for templates. Grooper 2.7 leverages computer vision to identify lines establishing header, column and row boundaries, resulting in the rapid and accurate capture of information from even the most complex tables.

Multi-Language Processing Supports Globalization

Grooper users can now capture foreign text and translate it into English. Grooper 2.7 ships with a comprehensive multi-language support database and recognizes 268 languages and 523 regional subcultures. Objects like data formats, content types and field classes are now language-aware. Grooper 2.7 also interprets culture-specific date, time, currency and numeric formats.

(While the new multi-language support in Grooper 2.7 allows for the recognition and processing of text in multiple languages, Grooper’s user interface is currently available only in English.)

Learn more about Grooper 2.7 and request a demo at

About Grooper

Grooper is the world’s leading software platform for discovering data and transforming it into actionable information. Grooper leverages sophisticated artificial intelligence, delivering a robust feature set that unlocks valuable business insight and fuels innovative analytics technologies. By digitizing and normalizing important documents, Grooper also ensures they are preserved and accessible over time. Organizations are tapping into the power of Grooper to better understand their data, accelerate workflows and gain a competitive edge. Founded in 1986, BIS, creator of the award-winning Grooper platform, is a visionary in the information management space.

Download a PDF of this press release here.

Give it a Try

The Grooper Experience Will Change You

Let's Get Started!