We use cookies, just to track visits to our website, we store no personal details. Find out more...

Rich Feature List

Industry leading accuracy and reliability are the driving forces behind Transym. However, over the last decade we've refined TOCR to the point where it now offers an impressive range of benefits for integrators:

Designed for integration – with free development software

A non-invasive piece of software, TOCR is designed to be integrated into your solution with as little disruption as possible.

  • You get free API as standard with both full and trial TOCR versions.
  • Example routines are provided in C, C#, Visual Basic, VB.Net, Delphi and Python to enable fast integration and to provide working solutions.

Reliable – fewer mistakes, less downtime

Failure to recognise characters and words results in a high number of reported errors and can cause some OCR software to crash or hang. During unattended or batch processing of large amounts of data, this is a significant problem and seriously impairs productivity (and therefore profitability).

  • TOCR is one of the most stable, accurate and reliable engines on the market.

Transym's intensive testing and training process utilises over 108,000 image files, producing an engine that is not only highly accurate but also extremely robust. This minimises the number of errors encountered, and maximises the efficient handling of those that do occur.

PDF Support

TOCR now supports PDFs, Our new API supports extracting pages from PDFs and producing a bitmap (DIB) to be processed by TOCR. The results can then be saved as an appendix which would allow text from within PDF images to be searchable.

Font independent

New in version 5 we can return the font information and whether the font is normal or italic.

But because recognised text is primarily used for searching or formatting we don't focus on the font that has been used for character recognition.

Instead we have optimised TOCR to recognise the characters and allow you to set the font in which you wish to view or export the text. This makes it much simpler and quicker for you to process a batch, without fiddling around with different settings.

For users with data in the OCRB font, there is an additional option to flag this font for more accurate processing, at the expense of accuracy with other fonts.

Maximum character accuracy

There are dozens of things that can interfere with an OCR engine's ability to accurately read a character. From broken letters to underlined text – all of these hurdles can slow down performance and increase the need for human intervention.

  • Through our testing process, TOCR is trained against real life multi-lingual examples of documents and images that have been subject to such distortions.
  • TOCR's ability to recognise is optimised for maximum character accuracy – saving you time, effort and money in the long run.

Maximum word accuracy – in  45 different languages

In some circumstances a character can be recognised correctly but in the context of a certain word it can be incorrect. For example, in many fonts the image for o and 0 or 2 and Z can not only be similar, but in some cases identical.

Just recognising the character is therefore not enough, some reference must be made to a collection of commonly used words to choose the right option.

Most other OCR solutions use libraries or dictionaries to perform this function. These are static repositories which are language specific and can struggle to cater for the adoption of new words or the inclusion of quotations and phrases from other languages such as French or Latin which are commonly used, especially in legal and medical documents.

At Transym, we use a lexicon which includes words and phrases from many languages, living or dead, to provide a single source of reference offering outstanding word accuracy and reliability. Setting Lex on improves accuracy by using the context of the character and those around it.

  • TOCR offers up to 99% accuracy in English, French, Italian, German, Dutch, Swedish, Norwegian, Finnish, Danish, Spanish, Portuguese and more. You can see a full character map here.
  • In addition, on very poor quality documents or where characters have been badly reproduced, TOCR will provide up to four suggested alternatives during word accuracy checking and carry on processing so that the document or batch can be completed and the checking process can be performed in the quickest time possible.
  • The Auto-Lex option allows TOCR to automatically decide whether to use the lexicon function for a given image.

Optimisation for poor backgrounds

The quality of the background (for example, photocopied, faxed or crumpled documents) can also have an impact on character recognition.

TOCR is tested and enhanced using extremes of light and dark backgrounds, deformation and speckle. It is hardened using a vast source of imperfect samples to train the software to identify text as opposed to background defects.

Colour Conversion Options

TOCR supports colour images by using colour conversion algorithms that convert colour images to monochrome.

You can choose between 9 different options to best suit the colour conversion of your documents. These options include:

  • Desaturation
  • Decomposition
  • Filtering out Red
  • Filtering out Green
  • Filtering out Blue
  • And more...

Automatic orientation detection

TOCR automatically detects which way up the image or page has been scanned and delivers the recognised text the right way up.

Image & Font Information Return

TOCR is now able to return font information; the font face or family name as well as if the text is italic or normal.

TOCR can now return the image used for recognition which will include any rotation and deskewing done by TOCR before processing.

Scalable performance

Although TOCR only requires a single processor PC running Windows Vista or later, for large scale solutions it can be scaled to run on up to 255 Processors on a single machine. Ideal for integrators.

TWAIN interface

TOCR's simple TWAIN interface allows users to send an image to OCR directly from their image scans, with no intermediate steps.

Speed switches

TOCR can now be adjusted for higher speeds when needed. There are four speed switches available - slow, medium, fast and express. An increase in speed will result in some loss in accuracy. For more detailed information on the speed switches, please visit our speed versus accuracy page.

Exceptional support and assistance

Transym offer a personal level of support that few other companies can match. While we endeavour to make sure that our system is as easy to use and reliable as possible, our support team are on hand to answer any technical or account questions that you may have.

Want to find out more? Click on any of the following: