GdPicture.NET OCR Engine: Improvements and New Features

MURET, France - Oct. 28, 2019 - PRLog -- Enhancement of the OCR engine

• Dramatically reduced average processing time. The engine may be up to 20x faster on very complex documents.
• Better text writing direction and orientation detection.
• Improved detection in bitmap with non-uniform backgrounds.
• Better text detection in complex regions with noise in the background, diagrams, and dotted areas.
• Dramatically enhanced PDF-OCR generation.

Integration of external engines

Since version 14.1.39, it is possible to link any external OCR engine to a GdPicture.NET application during PDF/OCR generation.

A tutorial is available in the documentation.

A few facts about the GdPicture.NET OCR engine

• 130 languages are recognized.
• Thanks to the research work made for building the GdPicture.NET MRC compression engine, the adaptive pre-processing and pre-segmentation phases leverage subsequent OCR accuracy and speed.
• The post-processing phase allows an excellent reprocessing of false-positive results, thanks to many years of experimentation on millions of documents.
• The Tesseract-based OCR engine has been modified to be continuously optimized to match the performances (and often exceeds them on complex documents) of established competitors.
• GdPicture.NET OCR includes multiple of its own segmentation engines.

About ORPALIS

ORPALIS is specialized in automating large-scale document-based processes, providing document imaging and document-management toolkits, as well as software tools for the general public. ORPALIS is the creator, developer, and owner of the comprehensive document imaging toolkit series released under the brand "GdPicture," now a worldwide known and respected leader in the imaging technologies industry. More than 13,000 developers based in over 70 countries have included GdPicture components in their applications. In 2011 ORPALIS releases PaperScan, marking the beginning of a new line of products meant for end-users. PDF Reducer is launched in 2013. In 2015 a most powerful universal HTML5 viewer and document management kit called DocuVieware is made available to the public. The same year, a software tool for converting scanned documents to the searchable PDF/OCR format, the ORPALIS PDF OCR, is launched. In 2016 DocuVieware Lite Free HTML5 Document Viewer is released. PassportPDF, released in 2018, is a modern cloud infrastructure offering freemium microservices via the AvePDF web application which addresses document management challenges of professional and general public users.

Contact