InftyReader

InftyReader is OCR software to recognize scientific documents including mathematical formulae, and to output the recognition results into various file formats: LaTeX, MathML, XHTML, HRTeX, IML.
It is developed in the laboratory of M. Suzuki, Faculty of Mathematics, Kyushu University, in collaboration with several cooperation partners.

The software recognizes only Black and White, and Binary images carefully scanned in either 600 DPI or 400 DPI. Please be aware that the program fails to run if the imput image contains gray scale image areas or color image areas even partly.
Image files have to be prepared in either TIFF, GIF or PNG format.

InftyReader outputs the recognition results in various format: IML, LaTeX, HR-TeX, XHTML(MathML).

IML is a XML file format related to InftyEditor, an editor of mathematical documents developed in InftyProject and released from Science Accessibility Net.
Using InftyEditor, user can correct and edit the recognition results of InftyReader comparing the results with original images, and convert the results into various formats mentioned above.

HR-TeX is a simplified LaTeX-like notation easier "to read" specially designed for the blinds.

In XHTML output, mathematical expressions are output using MathML notation.

For further details about this tool and how to try it, please go to the InftyReader's project website.