OCR & Text Searching

13th Apr 2015

Many clients ask me “do I need OCR technology”? The answer to that question depends on the nature of your digital data. But more importantly it depends on whether you are text searching your documents. By the way, OCR stands for Optical Character Recognition and is any technology that is recognising text in an image and creating useful searchable digital text data.

OCR – why use it?

Used in scenarios such as:

  • Scanning of documents received as normal mail
  • Fax network files – usually stored at .tiff image files
  • Scanning of documents in archive storage boxes

OCR – how to do it?

There are a range of OCR technologies depending on the amount of scanning and desired level of automation.

  • MFD manufacturers may incorporate on their equipment
  • Standalone applications for processing individual documents
  • Network based products that crawl all network data

OCR – what then?

OCR text is not very useful on its own. To do anything useful with the text data you will need searching technology such as that found in a document management system (DMS). Ideally, the scanning and OCR technology should integrate with the search technology.

If you think you have a lot of data that is not searchable then OCR is a technology that is worth considering. But start with the end in mind. What do you want to do with this text data?

Want to implement OCR? Ask us how.

 

Anthony Ridley- Smith

anthony@matrixsolutions.com.au

About Matrix Solutions

Matrix Solutions provides tailored hosted desktop and network management solutions to professional firms. In addition, the company specialises in installation and support of Worldox Document Management software. For more information about Matrix Solutions visit us at www.matrixsolutions.com.au.