CVision has leveraged its pattern recognition expertise to develop what it terms as "Super Fast" OCR in the latest version of its PDF Compressor software. The software is named "PDF Compressor" because of its ability to create very small PDF files from scanned images. This is achieved through the application of segmenting and JBIG compression.
In PDF Compressor 5.0 CVision, an ISV based in Queens, NY, utilizes inter- and intra-page font learning to accelerate the OCR process. According to CVision founder and CEO Ari Gross, "We can apply OCR 10 times faster than [a leading OCR vendor], with the same accuracy."
PDF Compressor 5.0 also features a "Super Accurate" mode that leverages font learning. In this mode, CVision boasts a 5-10% accuracy increase over leading OCR engines. This is based on word accuracy.
It's probably important to note that CVision does not develop its own OCR technology. Rather, for PDF Compressor, it licenses Nuance's OCR toolkit and improves upon it with its proprietary technology.
PDF Compressor is a mature products with an install base in the thousands. There are versions available that can be integrated into the workflows of leading capture platforms from Kofax, EMC Captiva, and Oracle.
Subscribe to:
Post Comments (Atom)
1 comment:
PDF Compressor removes the duplicate PDF objects, optionally takes advantage of new compression features of latest PDF specifications. It allows you to shrink PDF file by using flate or runlength compression algorithm. Thanks a lot!
Post a Comment