FlexiCapture Review: Automating Test Form Capture with ABBYY

Dubai’s Transguard Group employs individuals from around the world, and nowhere is its linguistic diversity more apparent than in its facilities and cash management services, two of the firm’s largest businesses.

Transguard’s in-house training department offers English classes to help build a more capable and competitive workforce. A portion of the 38,000 full-time employees receives an English placement test on any given day, the results of which are entered into the training group’s proprietary application.

Initially, this entry was all conducted manually, with a problematic 75% accuracy rate. It was an awkward, two-step process, with one operator hand-writing the outcomes into a results form and a second operator typing the results form into the training application. Continue reading

FlexiCapture Review: OCR Enhances Classroom Learning

In fifteen years of instructing middle schoolers, Ontario teacher John Bouchard had worked with many students with reading and/or learning challenges. He found it effective to craft existing materials into new assignments and intensive study guides for those students, but the manual process of manipulating large amounts of text was practically a second job. In fact, he was not merely re-typing text, but physically cutting and pasting it to create new resources!

Frustrated by the immense workload, he began investigating OCR data capture and text-to-speech software, in hopes of automatically generating and consolidating class texts into listen-along versions for students who struggled to keep pace with the readings. Bouchard chose FlexiCapture’s counterpart, FineReader, which provides the same cutting-edge OCR engine in a package designed for single-user, low-volume deployments. Continue reading

Recognition Server Review: Great Price-to-Performance Makes Short Work of Library Digitization

The library system of the University of Southampton, an elite English institution, holds over 1.5 million books plus a far larger number of other documents. For its Library Digitisation Unit (LDU), the project of converting all this information to electronically accessible formats was daunting. Staff quickly recognized the necessity of an enterprise-scale OCR server to meet the goal of converting half a million pages per year from an extraordinarily wide variety of documents.

The LDU employed Recognition Server on everything from doctoral theses to 19th-century parliamentary proceedings to a particularly unique collection of antique books on knitting. Using just six book scanners and one line scanner to import text, the solution produced over two million digital documents, rendering rare and valuable works available to researchers worldwide. Continue reading