Hugo Vanwoerkom wrote:
Hugo Vanwoerkom wrote:
Jonathan Kaye wrote:
Hugo Vanwoerkom wrote:
Hi,
I've tried now about 5 times to post a thread on an OCR that is
opensource a Debian package and works fantastic.
But the post does not show up.
What's up?
Hugo
Hi Hugo,
This message showed up. Did you send this last one from the same
account as
the others?
Anyway I'd love to hear about the opensource OCR and I'm sure many
others
would as well. Can you give us the details?
The OCR is tesseract-ocr. These steps:
1. apt-get install tesseract-ocr
2. apt-get install tesseract-eng
3. use xsane to scan a page at 300 dpi and save as .tif
4. but that will be depth 16 which tesseract can't handle so reduce
the depth: convert foo.tif -depth 8 foo.x1.tif
5. run tesseract: tesseract foo.x1.tif foo -l eng
6. text will show up as foo.txt.
Works faultlessly with me: I have problems with single quotes and
dashes but he recognizes all words perfectly.
I have samples too, but let's see if this can be posted.
That went OK. Let me post the samples.
This is the page I scanned with xsane:
http://www.scribd.com/doc/9267859/p13x1
And this is the result:
http://www.scribd.com/doc/9269769/p13
As you can see the punctuation causes trouble, but a remarkable success
rate!
Well, what I just posted, I posted about 5 times yesterday and it never
showed up.
Who knows what happened.
Tesseract: very good!
Nice Christmas present! Thanks!
It is possible to train tesseract too, which I have not tried yet.
Hugo
--
To UNSUBSCRIBE, email to debian-user-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
