University of Cambridge > > Inference Group > Naive OCR?

Naive OCR?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Ryan Prescott Adams.

The ability of a program to ‘read’ the text displayed by other applications can be useful in several situations. Examples include screen readers (text to speech systems) for disabled users and general-purpose document annotation systems. While some computer applications support accessibility APIs that reveal on-screen text to other applications, a general-purpose system needs to be able to read text from the raw pixel image.

The problem, then, is doing “Optical Character Recognition” (OCR) not on scanned images but on screen grabs. In this talk I will explore the properties of on-screen text and consider whether “screen OCR ” could be done using a naive, lightweight approach which does not require prior knowledge of letter shapes. This is work in progress.

This talk is part of the Inference Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity