ORPALIS Imaging Technologies Announces Major OCR Improvements with Deep Learning-based ICR engine

The French company announces improvements in its machine vision capabilities with the release of its first ICR engine for handwritten recognition. Thanks to a robust and continuously improved OCR engine, the research and development team focuses on data extraction for business documents.

Muret, France, November 2nd

New ICR engine

ORPALIS Imaging Technologies introduces its first ICR engine, improving its machine vision capabilities. This first version is dedicated to handwritten numerics located in boxes, and future versions will support more contexts.

The ORPALIS OCR engine

The OCR engine found in ORPALIS’ flagship products like its SDKs GdPicture.NET, DocuVieware, and PassportPDF API comprises different continuously improved layers using heuristics, machine learning, and applied mathematic-based methods.

The OCR engine is continuously improved and produces faster results with better quality. It is starting to implement outcomes of extensive fundamental research carried by the R&D team for the past ten years. Research work includes thresholding, pattern recognition, layout analysis, and image quality enhancement.

Deep learning-based features help to increase the speed and accuracy of the engine and bring new capabilities such as ICR.