[Digikam-devel] Digikam-devel Digest, Vol 58, Issue 97

Aditya Bhatt adityabhatt1991 at gmail.com
Wed Mar 24 11:34:43 GMT 2010



I have a really simple problem compared to recognizing faces :) I try to
> detect the square areas around pictures in the preview on a flatbed image
> scanner.

Ah, I made a small, crude program named "Texas" a few weeks ago... it tries
to detect "objects" in images - you can tune it's parameters to detect
individual characters, words, lines, paragraphs, or images. It's made using
openCV and written in C++.
Texas also has an option to parse a comic book page and extract the
individual picture "boxes".

I had intended to use it for literally "compressing" text in scanned images
- that is, if there's too much whitespace left between lines or words, you
could move the lines/words a bit more "together" to save space in the
image... maybe I'll implement it one day :)

Not sure how useful it would be to you, you might want to give it a try :

Yep, as you and Michael noted 100*150 pixels is not enough for a group
> photo.
> The situation is a bit different for the scanner. There you probably do not
> want to have more than ~5 different selection and there a small resolution
> image is enough.
> The main idea could still be valid. The idea being to have a "two phase
> detection". The first phase would does a very quick inaccurate search
> (false
> positives?) and the second would only investigate the areas found in the
> first
> phase.

I'll think about it...
Aditya Bhatt
My Blog : http://adityabhatt.wordpress.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.kde.org/pipermail/digikam-devel/attachments/20100324/97fa77ad/attachment.html>

More information about the Digikam-devel mailing list