OCR Conversion and Processing
Convert your paper documents to fully editable electronic files using OCR Conversion
OCR (Optical Character Recognition) is a process of converting hard-copy documents to full editable electronic files such as Word documents, Excel spread sheets, XML, CSV, HTML, PDF searchable, database etc. The process begins by scanning the hard-copy material (eg. books, novels, newspapers, documents, magazines, journals, directories etc.), producing high-resolution images (eg. TIFF, PDF, JPEG etc.), converting the image to a machine-readable and editable format.
Our specialist OCR conversion services include scanning of various types and sizes of documents and converting those to our client’s desired format. The quality of the OCR recognised text depends on the quality of the source documents. For example, if the documents are printed on a fairly good quality printer and are clear/legible, the OCR conversion accuracy will be as high as 99.99%, however if your documents are old, faint prints, contains marks, scratches etc. the accuracy and the quality of the OCR recognised text will be effected.
For these types of documents, we provide the following further OCR services;
+ OCR Data Cleansing
+ OCR Data Proof-reading
+ OCR Data Restructuring (layout, format, fonts, pagination etc.)
Our OCR to Excel conversion services can be applied to structured (fully formatted tables with table gridlines), semi-structured (text, tables, images etc.) or non-structured (loose formatted). For example, if you have documents which are printed from an Excel spread sheet, a CRM system, bank statements, directories containing addresses and contact details we can convert these to fully formatted, accurate Excel spread sheet format.
We can further process the data and convert it to file formats such as CSV, XML, Text Searchable PDF, Sharepoint import etc.
OCR Conversion - How
does it work? 
The first step in the OCR conversion process is to assess the quality of the original documents to determine the layout and formatting. Once we have assessed the documents, scanning and OCR rules are configured. OCR tests are carried out and samples are created for our clients approval. We offer three levels of Optical Character Recognition (OCR) conversion depending on the quality of the original documents and level of accuracy required.
OCR accuracy depends on the quality of the original documents, if they are of fairly good quality, we can then achieve up to 99.99% accuracy.
There are three levels of OCR conversion available depending upon what you require:
OCR level 1
This is for the simplest of files which are plain text documents to be converted to a Microsoft Word document.
OCR level 2
This is for somewhat more complex file layouts which have data in tables, flow charts, differing fonts and / or graphics. If you need to keep the original layout fonts, page order etc. then we recommend level 2.
OCR Level 3
OCR level 3 is the most in-depth level and includes manual proof-reading and correction of any errors that may occur through the OCR process. This ensures that specific areas are double-checked, corrected and cleansed as required.
OCR Conversion
Languages
English 
French 
Spanish 
Portugese 
German
Plus all other major world languages
(Subject to sample testing).
Contact us for your OCR conversion / processing requirements
Please give us a call on 0845 22 55 923 or request a FREE online quote.
Local call: 0161 832 7991 (Manchester)
0207 183 1885 (London)
Contact us
ISO 9000 Accredited
Education
I recently emailed Pearl Scan two chapters of a book that I had scanned into a flat PDF and it came back to me within a day as a MS Word file. The cost seemed very reasonable, and it came from an individual who remains available to solve any problems.
Free Quote
Scanning Services
Software Products
Information
Our
Company
Contact Us
