If you’re getting persistent problems with your processed batches, check our tips for successful OCR to see if the problem can be easily resolved. If you have a more complex issue, please contact us.

We have no compatible versions for these, and nothing in development at present. In the long run it is our goal to make TOCR as universally available as possible, but for now see above for the Windows systems we do support.

It is a long term goal for us to develop a TOCR variant for these operating systems, but we have nothing in development at present. We’ve had some success running TOCR on Ubuntu under WINE, and it’s likely TOCR will work under WINE in other Linux distributions, but we cannot offer any technical support for this.

TOCR can read and convert English, French, Italian, German, Dutch, Swedish, Norwegian, Finnish, Danish, Spanish, Portuguese, Russian, Belarusian, Bulgarian, Bosnian, Catalan, Czech, Greek, Estonian, Basque, Croatian, Hungarian, Icelandic, Lithuanian, Latvian, Macedonian, Polish, Romanian, Serbo-Croatian, Slovakian, Slovenian, Albanian, Serbian, Turkish, Ukrainian, Luxembourgish, Galician, Neapolotan, Lombardian, Sicilian, Piedmontese, West Frisian, West Flemish, Limburgian and Sami.  TOCR is language independent, so there is no need to select a language before processing. We’re constantly looking to improve TOCR, including adding further languages in future.

You can see a full character map here.

TIFF is a container format that can be used for many different types of file. TOCR will not support all of these. TOCR uses the libtiff library, and you can find out which types of TIFF file are supported by TOCR at the libtiff library website here.

TOCR can read PDF (.pdf), bitmap (.bmp) and TIFF (.TIFF) images, and will convert these to text (.txt) files. If you wish to process any other formats, you will need to convert them either on input or output.

TOCR Version 5.1 does support PDF files, find out more here.

No. But we have sample code that demonstrates an interface to .NET (visit our downloads section).

Up to TOCR 3.3, all code written for older TOCR versions was compatible with more recent versions. Code written for TOCR 3.3 and earlier is compatible with the 32-bit variant of TOCR 4.0, but not the 64-bit variant.

Microsoft Visual Basic and C are supported. However, provided you convert the “declares” and “structures” correctly, there is no reason that the routines cannot be called from any language capable of calling standard Windows API functions. Please note that whilst we have included Delphi and Python sample source code, we do not offer technical support for Delphi or Python.

If you are moving one or more TOCR installations to a new system and need information on how to uninstall licences from your old system(s), please see here for uninstallation instructions.

In order to have a fully working version of TOCR, you will need to have downloaded and installed the correct version. Once you have purchased a copy of TOCR, you will then receive an e-mail from our vendor, MyCommerce, containing your licence key and a download link for the TOCR licence pack. You will need to install the licence pack over TOCR, and input your licence key. If you do not receive an e-mail from MyCommerce, please check your spam and junk e-mail folders

Not at this time, however we do have a reseller licensing model that is intended for bulk users.

No. You must first purchase a licence for each OCR engine that runs on any machine.

If you have purchased Versions 1 or 2 of TOCR and wish to upgrade to 3.3, 4 or 5.1 you may purchase an upgrade licence from our purchase page.

If you have purchased TOCR Version 3, you may upgrade to Version 5.1 free of charge. Simply download Version 5.1 from our download page, and install it over your licensed copy of Version 3.

If you have a copy of TOCR Versions 1.0 to 1.3 and wish to upgrade to Version 1.4 for free, please contact us to find out how to do so.

We strongly recommend using TOCR 5.1, which is our most up to date version. Version 5.1 is a free upgrade to Versions 3 and 4 and use the same licences.

TOCR Versions 1 and 2 have now been legacied, please contact us if you need to buy licences for Versions 1 and 2.

We do not differentiate between standard and server licences, TOCR always costs the same per CPU core.

A standard TOCR licence allows you to run one TOCR engine on one machine. This means TOCR will run on one CPU core of any given machine, unless you purchase additional licences for additional cores. Extra licences will allow you to start multiple TOCR engines or instances, with a maximum of 255.

In order to have a fully working version of TOCR, you will need to have downloaded and installed the correct version. Once you have purchased a copy of TOCR, you will then receive an e-mail from our vendor, MyCommerce, containing your licence key and a download link for the TOCR licence pack. You will need to install the licence pack over TOCR, and input your licence key. If you do not receive an e-mail from MyCommerce, please check your spam and junk e-mail folders

You can process up to 50 A4 documents for free with our TOCR 4.0 and 5.1 trial. Once this limit has been reached, you can purchase a full licence here.

Yes. While we make great effort to make TOCR easily scalable for integrators and large businesses, TOCR is also ideal for smaller enterprises – offering unbeatable accuracy and a simple to use interface.

TOCR 5.1 is a free upgrade for users of TOCR Version 3 & 4. Users with licences for TOCR Version 1 and Version 2 can upgrade to Version 3,4 or 5.1 for GBP £35.00. Please see our purchase page for more information.

You can download free sample code for all TOCR versions here.

You can find information on how to interpret character positions in our sample documentation here.

TOCR does not currently support OCRing of zones (regions of a page); it will always OCR the whole image. If you wish to OCR zones then you should either:

a) OCR the whole image and extract characters based on the positional information returned or
b) Copy the zones to a new image and OCR the new image.

Accuracy is usually much improved if all the zones are OCR’d at once rather than OCRing the zones individually. To do this copy the zones to a clean image and separate them vertically, with lots of white space.

The speed at which TOCR runs is hugely variable depending on a number of factors, including: the speed and capacity of the machine and the type of data being processed. As a result it is impossible for us to give a general figure for processing time. We recommend running your own tests.

Since Version 3.3 TOCR has included a speed option facility. Speed options can be 0 (default), 1, 2, or 3, from slowest (0) to fastest (3). The options tell TOCR how exhaustive it should be in looking for improvements. There is a small loss in accuracy with increases in speed options. For more detailed information on speed settings please visit our speed versus accuracy post.

Lex processing is Transym’s unique technique for correcting common OCR mistakes. It does not use standard dictionaries; it uses character frequency/probability tables. This allows TOCR to cope with new words and common misspellings. Setting Lex on improves accuracy by using the context of the character and those around it. TOCR 3.3 for the first time allows TOCR to automatically decide whether to use Lex when processing an image.

TOCR will accept these images, but they are converted to black and white before processing. We have 9 different colour conversion algorithms to choose from.

There are many reasons why TOCR may not be able to process a particular image that are common to all OCR engines, and are an ongoing challenge for OCR in general. In particular, noise, faint or broken characters, overly bold or black characters, merged characters, and text embedded within a picture can decrease accuracy. Whilst TOCR is an extremely accurate OCR engine, it will not get everything right. See our OCR Tips page for more information, and advice on improving results.

The character map for version 5.1 can be downloaded here. The character map for Version 4 can be downloaded here. The character map for Version 3 can be downloaded here. (Version 4 now recognises superscript characters 1,2 and 3: ( ¹ ² ³ ), the trade mark symbol: ™ and per mille sign: ‰ whereas Version 3 does not). For users still using Version 1.4, the character map can be downloaded here.

This is supplied when you buy a licence. The documentation is written in C, but TOCR can be used with other languages as described above. You can also download some sample documentation from here.