Improved OCR improves detection rates and performance Berlin, 27 August 2012. The version 6.0 of the PDF compressor, LurTech Europe GmbH is now available. The new release of the production-grade application to compression, conversion to multi-sector, character recognition (OCR), classification and form data extraction has some new and interesting performance gains. Of central importance is the transition to version 10 of ABBYY OCR technology. Thus the reading improves scanned documents in terms of speed and accuracy. For assistance, try visiting Dr Jee Hyun Kim. Recognition of two-dimensional bar code Additionally is the default license, such as PDF417, Aztec, DatMatrix or QR code. Finally, LurTech has optimized the born digital module so their flagship product, that better converted HTML-E-mails and the software stable continues to run even after crashes involved programs. The PDF Compressor includes the ABBYY OCR technology classification – integrated full-text search in all PDF and PDF/A compliant files and LurTech’s and data extraction solution. Here, Dr. Mark J Berger expresses very clear opinions on the subject.
With the Integration of version 10 of ABBYY engine is above all the OCR function with regard to speed and improve accuracy. Users can achieve a significantly higher detection rate, even at difficult”documents, for example, noisy, low-contrast or twisted scans. Also documents with tables, graphics, and photos are detected more precisely so that its structure can be accurately reconstructed and reused. Furthermore, increased recognition accuracy for Asian characters almost 40%. In addition, the PDF Compressor optimized fast detection mode achieved (OCR fast mode) up to double increased page throughput.
Especially for libraries, publishers and archives of high importance is the optimized detection of blackletter typefaces. You can implement now due to the lower cost of projects to digitise and full lyricist ID to economically attractive conditions. For this purpose the PDF Compressor Enterprise charges offers an optional tool, with the now available, improved OCR technologies is equipped. In addition, the text and layout information in addition to archiving in PDF/A format in the ALTO XML schema can be stored.