Capturing Data Automatically with EDAC and Parascript

By CIOReview | Monday, August 8, 2016
582
982
196

FREMONT, CA: Parascript LLC, a provider of data extraction software, announces the latest development in the EDAC Systems’ solution – ReadSCRIPT Maestro. Parascript and NITe technologies empower ReadSCRIPT Maestro to locate and separate handwritten words in unstructured fields. EDAC's word recognition product, ReadSCRIPT, receives handwritten email addresses forwarded and detected by Maestro.

Approaching the Data Extraction Challenge

ReadSCRIPT Maestro performs separation, recognition, and classification processes on each received document. EDAC’s PurePAGE – an automated solution for image enhancement – detects the quality as well as resolution of the image; scrubs and resizes the images if needed. PurePAGE uses a variety of methods such as deskew, de-speckle, de-shade, auto-invert, and black border removal to enhance the image quality. In case of low-resolution images, PurePAGE automatically determines the resolution and adjusts it to 300 DPI. In addition to image optimization, the quality of characters – important aspect while handwriting is concerned–is ensured by letter and character filling and smoothing.

Improving Accuracy during Capture

Optical character, intelligent character, optical mark, and barcode are recognized and one or multiple recognition engines are used to enhance the accuracy of document recognition and index extraction. To ensure accuracy, ReadSCRIPT performs intelligent word and phrase recognition. ReadSCRIPT uses over 25 dictionaries to validate the fields against entries in those dictionaries.

If the system fails to ascertain the document type or the extracted data, then it switches to a verification queue where the type and data can be manually reviewed and corrected. ReadSCRIPT Maestro helps to locate and classify the individual words and lines even if the document or specific fields are written in cursive and are part of unstructured documents or fields. Parascript technology recognizes the words in the snippets received from Maestro.

“We have found that introducing ReadSCRIPT and Parascript to a manual keying project, reduces error rates, processes documents faster and can literally save our customers millions of dollars by reducing manual data entry,” said Randy Blevins, founder of EDAC.