Thursday, January 10, 2013

Using OCR In Enterprise Content Management Software

In its simplest form, OCR (Optical Character Recognition) Software consists of extracting text from images. According to Wikipedia, it is the mechanical or electronic conversion of scanned images of handwritten, typewritten or printed text into machine-encoded text…It is a common method of digitizing printed texts so that they can be electronically searched, stored more compactly, displayed on-line, and used in machine processes such as machine translation, text-to-speech and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision. 

We’d like you to see the video below, which shows that an image is worth more than a thousand words; you’d have to get your calculator out in order to get an estimate of how much it’s worth. ;-)

For sure, “interacting via a text editing program” has many implications:
  • being able to look for documents within our internet, document manager or corporate ECM platform, conducting a full text search, or maybe while looking within the document. 
  • being able to pass the document (in .TIFF, .JPG, unindexed .PDF, .PNG or any other image format) to a Word (.doc) format, Open Office (.odt) or any other editable document format that we choose, so that we can edit and improve the text. 

This also has its own implications in the Intelligent Document Management field, which we, at Athento, are moving on:

  • We can convert information into metadata automatically, since we can already reason about the content of the documents; 
  • We can improve the result of any OCR software via ICR; rather, we have the capacity to infer, in an automatic way, the content of a word that could not have been scanned correctly (because the paper was folded at a corner, the ink on the paper was smudged, or for any other reason.)

There are other exclusive solutions, such as Kofax and Abby, and many others, which can be integrated with ECM.

As always, the advantage of our OCR is that it’s based on open source code, which gives it the advantage of having a much better price, without losing any of the tech power; and, winning, more than anything, with freedom: you can choose another business to develop the software that we provide to you, if you feel that that is necessary, without any kind of limits.

Additionally, these proprietary solutions can mean significant prices increases: normally, you buy a license for each user, so if your organization has two thousand users, you’ve got to multiply the cost per license by two thousand (with the corresponding volume discounts.)

In the case of our OCR module, the cost is only the cost of implementing the system. We’ll charge you for the motor of the car, but we don’t care if you drive the car while it’s full of passengers, or if you go by yourself. We don’t get involved in that.

Evidently, and especially when an organization reaches a certain size, the cost goes from being a fraction of the system of exclusive OCR systems, without losing trustworthiness (unlike exclusive solutions, which don’t incorporate semantic technology to perform ICR (Intelligent OCR).

You can see more videos on Yerbabuena Software’s YouTube channel.

 Popular posts:
Comparing Document Capture Solutions (Athento, Kofax, Ephesoft etc.)
Document Management Success Case at BBVA, managing 7 million records.
Comparing ECM Systems (including Alfresco, OpenText, Documentum, Filenet, Sharepoint or Nuxeo).

LikeUs Yerbabuena Software on LinkedIn Share

1 comment:

  1. Hi,

    Very informative and helpful post. I found as I am searching for the best OCR software and I got this download link that let try there software.