> I opened a page of text from the NY times in print mode, and captured
> a portion of the screen.

OCRopus hasn't been trained on screen captures, and screen captures
require very different parameter settings.

> I usually use to read. I measured a lowercase h in pixels, it's 14
> pixels high and 10 pixels wide. Maybe that's too small?

Yes, OCRopus isn't set up to handle text of that size.  A 12pt "h" at
300 dpi is about 35 pixels high.

> Does ocropus want the entire image to be just
> text?

Right now, there is no text/image segmentation in the command line
tools.  If you run OCRopus on 300 dpi images, the text line finder
does a pretty good job at text/image segmentation.

> We'd
> like it to be able to do a lot more, but I'm just
> exploring some possibilities here.

Have a look at the Python examples in ocropy; we'll be adding
documentation to that.

Tom

-- 
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en.

Reply via email to