InftyReader Group, Inc.
Established in March, 2007, InftyReader Group, Inc. offers a sophisticated optical character recognition application that is used by thousands of universities to recognize, convert, and enable the editing of Science, Technology, Engineering, and Math (STEM) educational content (both print and digital) into accessible formats in support of students with print disabilities. A print disability is a condition related to blindness, visual impairment, specific learning disability or other physical condition in which the student needs an alternative or specialized format (i.e., Braille, Large Print, Audio, Digital text) in order to access and gain information from conventional printed materials. InftyReader is an Optical Character Recognition (OCR) application that recognizes and translates scientific documents (including math symbols) into LaTeX, MathML and XHTML.
InftyReader Group, Inc. embraces the “SciAccess mission” to:
“Enhance the accessibility of STEM-related educational materials by individuals with disabilities”
Software Reference Documents:
- InftyReader: An OCR System for Math Documents (115 KB Word Document)
- Important InftyReader User Guidelines (243 KB Word document)
InftyReader is an Optical Character Recognition (OCR) application designed to convert Science, Technology, Engineering, and Math (STEM) educational content (both digital and print formats) into LaTeX, MathML, and/or Word XML in support of K-20 students with print disabilities.
What is a print Disability?
A person with a print disability is an individual who cannot effectively read print because of a visual, physical, perceptual, developmental, cognitive, or learning disability. A print disability prevents a person from acquiring knowledge from printed materials in a standard way, and requires them to use alternative methods to access that information. Print disabilities include visual impairments, learning disabilities, or physical disabilities that impede the ability to manipulate a book in some way.
What are STEM Documents?
Science, Technology, Engineering, and Math (STEM) documents may include any/all of the following:
- Math/Chemical Formulas
- Flow Charts
- Figures and Graphs
Why can’t some individuals with a print disability access mathematical content?
- Often, images of mathematical equations, appearing on web pages, in print, in eBooks, and PDF documents, are not accessible by students using Assistive Technology;
- Most math content cannot, easily, be converted into alternative output modalities, such as Braille or synthetic speech;
- Most math content cannot, easily, be altered to accommodate the learning needs of students with low vision (color, font size, and contrast changes); and,
- Making math accessible would require authors to redraw images constantly, even when small changes are made.
What, exactly, does InftyReader do?
InftyReader recognizes and translates image-based scientific documents (including math symbols) into LaTeX, MathML and XHTML. InftyReader can recognize tables including math expressions in the cells so long as the ruled lines are not broken.
InftyReader incorporates the use of three OCR engines. The first is InftyReader’s own OCR engine which has been designed to recognize scientific and mathematical symbols in formulae. The second and third OCR engines are from the Toshiba Corporation (ExpressReaderPro) and MediaDrive Corporation (WinReader). The ExpressReaderPro and WinReader OCR engines operate simultaneously in order to improve the recognition results of characters appearing in ordinary text areas.
InftyReader does not convert PDF files containing gray-scale, text, or color images. Once, again, InftyReader can only process black and white images (binary images). Original PDF documents must contain high resolution 600 Dots per inch (DPI) scanned images in order for InftyReader to work effectively. Web-based PDF files often contain low resolution images (<300 DPI) in order to reduce download and load times. In such cases, the recognition results will be useless.
InftyReader System Requirements:
- Windows XP, Vista, Windows 7
- 1 GB (or more) of system memory;
- Internet Explorer
- Note: InftyReader does not run on Windows 98, Me, or 2000.
Maximizing the Accuracy and Effectiveness of InftyReader:
- All source documents must be clearly printed.
- All images need to be “binary” images scanned at 600 DPI. InftyReader will eliminate “noise” (smudges, pencil marks, some highlights, etc.) so long as the “noise” is minor and do not cover any of the text being scanned. To get better recognition results, users are encouraged to delete all markings from documents before OCR’ing them with InftyReader.
- Adjust the binarization threshold of the scanner you are using so that the percentage of the “noisy” or broken characters is less than 1% of the total number of the characters in each scanned page image. If this is not done the accuracy of the results will be negatively impacted
About ChattyInfty Version 2 Series:
ChattyInfty is a talking math editor designed to enable student with print disabilities to “listen to math equations being read to them through the use of a speech synthesizer. It can export files into the following formats: LaTeX, HTML, MathML, Human Readable TeX (HrTeX), Word 2007, Spoken Text (entire document, current paragraph and selected text), and Word XML. Can Import files of the following types: LaTeX, image files (TIF, BMP, GIF, and PNG), and Scanner.
Important Note: ChattyInfty is an extended version of InftyEditor with a plug-in speech interface to output the content of editing data in TTS generated by InftyReader. In order to scan images into ChattyInfty, InftyReader is required. ChattyInfty can speak math expressions, accordingly to the cursor movement. It is an editor of math documents with voice output, usable by people with visually impairments.
About ChattyInfty Version 3 Series:
ChattyInfty Ver.3 series is an authoring tool of Multimedia Daisy and accessible EPUB3 eBooks.
ChattyInfty Version 2 Series was developed on top of the base code of ChattyInfty Version 2 Series. In addition to the same features as ChattyInfty 2, ChattyInfty 3.0.3 offers the following features:
- Has an easy and intuitive user-interface to edit the heading structures of documents (chapters, sections, subsections),
- Edited results can be saved as:
- DAISY2.02 with voice in SAPI5, math expressions as image
- DAISY3 (Text Daisy) with math expressions in MathML
- EPUB3 with voice in SAPI5, math expressions as image
- Users can control the reading of the texts and math expressions in different ways
- Click here to download the documentation
InftyEditor is an authoring tool of mathematical documents. It makes creating and editing mathematical expressions easy and intuitive.
Important InftyEditor and ChattyInfty Notes:
- You need to download and install our LaTeX Installation Kit to install all the components of LaTeX necessary to run InftyEditor’s/ChattyInfty’s LaTeX functions. For more detail, please see TeXSetup.txt.
- You will need to install Math Fonts in order to use InftyEditor/ChattyInfty. See the Math Fonts section below.
- InftyEditor Manual (500 KB download)
- InftyEditor List of Symbols (150 KB download)
LaTeX Installation Kit V3.0
Free! (57 MB download):
Using this installer, you can install all the packages of LaTeX required in InftyEditor’s LaTeX functions.
For more detail, please see About TeXInstaller 3.0.
To download the package file, please click the following:
- TeXInstaller Ver.3.0 fullset (about 230MB) , TeXInstaller Ver.3.0 smallset (about 90MB without documents)
Download Math Fonts:
Math fonts maybe freely downloaded from: