http://john.mignault.net/blog/2007/10/25/ocropus-garden/ Drawing diabetic comics-reading pen-fetishizing cycling leftist geek librarian. God, how bourgeois. Sun, 22 Jan 2012 19:30:00 +0000 hourly 1 http://wordpress.org/?v=3.2.1 http://john.mignault.net/blog/2007/10/25/ocropus-garden/comment-page-1/#comment-3351 jbm Mon, 29 Oct 2007 15:55:11 +0000 http://john.mignault.net/blog/2007/10/25/ocropus-garden/#comment-3351 Not sure; we don't really have any yet either. My guess would be that it probably does in some way given the recent distributed Captcha stuff to help improve IA's OCR. Anyone else want to chime in here? Not sure; we don’t really have any yet either. My guess would be that it probably does in some way given the recent distributed Captcha stuff to help improve IA’s OCR. Anyone else want to chime in here?

]]> http://john.mignault.net/blog/2007/10/25/ocropus-garden/comment-page-1/#comment-3350 Andy Mon, 29 Oct 2007 15:51:02 +0000 http://john.mignault.net/blog/2007/10/25/ocropus-garden/#comment-3350 The Ars review mentions Aspell and language data files, which suggests that OCRopus should be able to at least recognize that its output is wrong: if OCR'd words don't match a dictionary file, it should flag them as problems. I've no OCR experience; is that how it normally works? The Ars review mentions Aspell and language data files, which suggests that OCRopus should be able to at least recognize that its output is wrong: if OCR’d words don’t match a dictionary file, it should flag them as problems. I’ve no OCR experience; is that how it normally works?

]]>