Scan Centers of America® offers the full spectrum of Electronic Document Management (EDM) services.

OCR / ICR Cleanup

Sample Definitions:

Optical Character Recognition (OCR): A technology that can recognize letters from a scanned image and convert them into ASCII characters to be saved as an editable text file.
Intelligent Character Recognition (ICR): The ability to read any printed text regardless of typeface
OCR converts scanned images comprising pixels into editable text.

Document image files have limited utility unless you have the ability to search and manipulate them. OCR is the process of extracting text from images. Axiom utilizes a number of different OCR conversion packages, each of which has its own strengths for certain types of documents. We tailor the OCR process to the specific requirements of a project and carefully analyze client needs and intensively test alternatives before recommending the OCR engine.

Tables and graphics (logos, signatures, etc.) are not a problem. Our OCR solution interprets tables and retains their original cell structure. Graphics are omitted from the OCR process to ensure they are not tampered with, distorted, or lost. You are able to study the OCR'd text and graphics in the same view so the look and feel of the original document is fully retained.

The OCR process allows our clients to search for keywords and if needed "copy and paste" sections of the text within the document. The accuracy level provided by this automated conversion technique is directly related to the quality of the source documents. For original, first-generation documents, accuracy levels exceeding 90% should be realistically expected. OCR is a cost-effective option and offers the quickest turnaround time, as there is minimal operator intervention. If even greater accuracy levels are desired, we recommend Manual Cleanup of the documents.

Some features of our OCR services:

Support for multiple export formats such as PDF, Word, Excel, and many more (see list below).
Our software offers multi-language support.
Support for legal and medical dictionaries.
Multiple computers are pooled together to optimize the OCR process.
OCR solution also offers multiple OCR engine voting for enhanced accuracy.

Document Export formats include:

AdobeÒ Acrobat PDF
MS Word 2003/XP/2000/97/95
MS Excel 2003/XP/2000/97/95
MS PowerPoint 2003/XP
Rich Text Format
Text; Unicode Text, ASCII
HTML; Unicode HTML
DBF; CSV; Unicode CSV
XML
Other Word Processing formats (WordPerfect, Star Office, etc.)


Go Back...

Resources | Legal | Contact Us
©2006 Axiom™, All Rights Reserved