Do you want to minimise errors in your scanned documents?
document scanning.net use the latest Optical Character Recognition (OCR) and data capture to reduce error rates by 65–80%.

OCR software works by:

• Passing the image through several software engines
• Each engine votes on what it thinks a character in a word should be (for example a 0 or a O)
• Changing the character to whichever gets the most votes (for example if there are two votes for 0 and 1 vote for O then the software will change it to a 0).

OCR software can be configured with different accuracy ratings depending on your requirements. Cost varies depending on the accuracy required but the highest level of accuracy may be more cost effective when associated costs for manually correcting errors or sifting through fuzzy search results are taken into account 

Phone 0800 197 2804 or click on the Live Chat Button to talk to an online advisor.

Frequently asked questions

Q1 What is the quality of the OCR?

The quality of the OCR depends on the master document, if the document is in good condition the results will be excellent, allowing search results to be around 99% accurate. If the document is old or characters on the page are of a poor quality then the acuracy results will reduce.

OCR technical information:

PrimeOCR

Prime Recognition developed PrimeOCR for the production marketplace to reduce the error rate typically found with conventional OCR engines. PrimeOCR includes the best retail OCR engines from ScanSoft, NewSoft, and Expervision. Your image is passed through each engine and using Voting technology, PrimeOCR reduces overall OCR error rate by 65-80%.

PrimeOCR can be configured with level 3 accuracy reducing error rates by 65% or configured to level 5 accuracy which reduces error rates by up to 80%. Level 5 accuracy takes more time to process and is more costly, but depending on your application, may be more cost effective when compared with the costs associated with error correction or sifting through fuzzy search results.

ABBYY FineReader

ABBYY FineReader delivers superior accuracy in converting almost any type of documents, including various office documents, tables and spreadsheets, magazine articles, books, and even faxes and digital photographs. With its new ADRT™, an Adaptive Document Recognition Technology, FineReader is capable to recognise not only the text and basic layout of document images, but the logical structure of a document across multiple pages. The key features of ABBYY FineReader 9.0 include:

• Superior recognition accuracy and layout retention
• Re-creation of document logical structure and formatting
• Multilingual document recognition
• Results-driven interface – unmatched ease of use and productivity
• Digital camera OCR
• Accurate, fast and secure PDF conversion
• Instant screenshot OCR
• Direct export to a variety of applications