[PD] OCR with Puredata?

Mathieu Bouchard matju at artengine.ca
Thu Jun 2 18:48:46 CEST 2011


On Wed, 1 Jun 2011, Tedb0t wrote:

> Well, that's the beautiful thing about neural nets—it just depends on 
> how you train the net.  If you want the net to be able to recognize 
> tilted letters, you can add tilted letters to the training sets.

That would take a damn lot more elements in the training set !

> It looks like the defacto open ocr lib is 
> Tesseract: http://code.google.com/p/tesseract-ocr/  This would be great 
> to have in Pd.

What a name. I mean, it's geometry-related, but Tesseracts are about 
four-dimensional spaces. :}

> Incidentally, I can't see any reason why Pd would be "bad at it," since 
> the ANN external uses the C FANN library, which is likely what any other 
> library would use in the first place.

Reasons why a language would be bad at it are obviously because of what 
would be different, and not what would be the same. FANN would be the 
same, and the rest would be different.

BTW, [ann_som] is not using FANN, did you know that ?

  _______________________________________________________________________
| Mathieu Bouchard ---- tél: +1.514.383.3801 ---- Villeray, Montréal, QC


More information about the Pd-list mailing list