claraocr.org

ABBYY Fine Reader

The Abbyy Fine Reader software is based on OCR technology and creates texts from determined templates. It is possible to edit and search through these texts – whether they are scanned paper documents, PDF files or digital images. The files can be extracted from documents and images and easily be converted into formats which give easier access to the text. These can then be saved in DOC, PDF, XML, CDY or HTML formats. The Abbyy Fine Reader can be completely integrated into the popular Office applications, making it comfortable to use.

The Abby Fine Reader displays the read document in a two-window view, so that both the original and the converted document can be seen. It also features an in-built spellchecker. Small mistakes are still possible, but are normally picked up by the software. It can also copy the layout from newspaper articles and books, as well as independently detect the language a text is written in. Users have no problem getting to grips with the program thanks to its user-friendly user interface.

Operrating systems: Windows XP oder höher | ABBY FineReader 10 Pro

Readiris 12

The OCR program Readiris was developed by I.R.I.S, who were already specialising in Optical Character Recognition in 1987. Readiris allows users to convert handwritten and printed documents into text documents suitable for use with the computer. These can then be easily edited without having to be typed out again. Readiris 12’s specialty is being able to recognise 120 languages and their characters. This also includes languages which use non-Latin alphabets, such as Chinese and Russian.

The original text can be scanned in using a scanner connected to the PC. Readiris 12 can also be used with images in BMP, JPEG, PNG or TIFF formats. These scanned files are then saved in DOC, RTF, PDF or HTML. A training form in the handbook provided helps with conversions from handwritten pieces. Readiris 12 can also recognise layouts and tables. It is a text recognition software which can deal with many aspects of text recognition. The new version, version 12, stands out due to the fact it can work even faster.

Operating systems: Windows, Mac. | Readiris Home 12

Corel OCR-Trace

This program was developed by the Canadian company Corel, a company not only known for its text recognition software, but especially for its image editing and graphics software. CorelDRAW is one of the best-known vector graphics programs. Corel OCR-Trace comes as part of the CorelDRAW package.

An OCR program is a necessary part of CorelDRAW when image files need to be converted to vector graphics. This is where Corel OCR-Trace takes over and converts images for CorelDRAW, so it can be edited. Users need to start up OCR-Trace, scan in the image and then save this as a vector graphic. It is also possible to adjust the settings, such as the number of knots or the colour settings. The relationship between the quality and the file size depends on the image. Corel OCR-Trace is an irreplaceable tool for editing vector graphics. It can also be used to read scanned in text documents and convert them into files. OCR-Trace can recognise text in scanned documents with a resolution of more than 300 dpi. It comes complete with an integrated spellchecker which can pick up smaller mistakes.

Operating system: Windows | CorelDraw Graphics Suite X4

Adobe Acrobat

The Adobe Acrobat OCR software was developed by Adobe Systems. They brought the Adobe Reader out in 1993 which was then only available commercially. It was first possible to show PDF documents in the browser in 1996. Adobe has constantly released new versions since then, the latest being Adobe Acrobat version 9. Adobe Acrobat software is able to create, read and manage PDF documents.

This program, which is only available commercially, is also able to work with digital signatures and encryption technology. It is able to convert scanned documents into files which can be searched through, thanks to automatic character and text recognition. With Adobe Acrobat it is possible for users to scan in texts, have these digitally recognised by the software and then converted all in one step – users just need to select the right configuration. The OCR feature recognises the text and then saves it in PDF format. For a PDF document, the scanner resolution must be at least 72dpi.

Operating Systems: Windows, Mac, Linux | Adobe Acrobat Standard 9 | Adobe Acrobat Pro 9

BIT-Alpha

Bit-Alpha is perhaps not so well established as other character reading software. It can convert paper documents, PDF files and digital images into files which can then be edited and corrected. BIT-Alpha can automatically divide the documents into image and text areas, facilitating the character recognition. The program is also able to learn new typefaces, symbols and logos and use these later. According to the manufacturer, this adaptive OCR software has a very high accuracy rate with regards to character recognition. Each character is then shown with its accuracy rate.

BIT-Alpha is especially suitable for filing and processing historical documents. Data can be sorted and saved in numerical library systems. It is possible to prepare these quickly for the internet thanks to the programs ability to automatically adjust the text and picture formats. In addition, BIT-Alpha is one of the few programs that are able to read Gothic fonts and convert these into a more modern font. This software is also able to recognise and identify handwriting and signatures.

Operating system: Not specified

Scansoft OmniPage

Scansoft OmniPage software converts scanned documents, PDF files and images into text files. This is especially helpful when information is only available in paper or as a photographic image. OmniPage uses OCR technology to create a digital document which can then be worked on using a text-editing program. According to information from the manufacturer, the software has an accuracy rate of over 99%. This character recognition program is able to convert TIFF, PCX, DCX, BMP, JPG, GIF, PNG and MAX files into text files. PDF documents can also be converted into editable texts in the blink of an eye. By maintaining the original format, it is possible to create converted documents which look exactly like the originals.

The user interface is very easy to use, and the software is very versatile. One example of this is a feature which allows selected areas of a document to be selected, whilst not including others. These settings can then be saved in the program, saving time in the future when texts with a similar layout are used.

OmniPage can automatically recognise 56 languages and has its own dictionary for 19 of these. The program also offers users a management function which enables them to work simultaneously with several documents without losing track of what they’re doing.

Operating systems: Windows XP or higher | OmniPage 17