From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.io/gmane.comp.tex.context/3788 Path: main.gmane.org!not-for-mail From: "H. Ramm" Newsgroups: gmane.comp.tex.context Subject: Re: river detection Date: Fri, 12 Jan 2001 15:57:27 +0100 Sender: owner-ntg-context@let.uu.nl Message-ID: <3A5F1B52.C08D9FD3@gmx.net> References: <3.0.6.32.20010110092703.015d1670@server-1> Reply-To: fiee.visuelle@gmx.net NNTP-Posting-Host: coloc-standby.netfonds.no Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Trace: main.gmane.org 1035394505 20132 80.91.224.250 (23 Oct 2002 17:35:05 GMT) X-Complaints-To: usenet@main.gmane.org NNTP-Posting-Date: Wed, 23 Oct 2002 17:35:05 +0000 (UTC) Original-To: ConTeXt Xref: main.gmane.org gmane.comp.tex.context:3788 X-Report-Spam: http://spam.gmane.org/gmane.comp.tex.context:3788 Hans Hagen wrote: > I think [but thanh may disagree] that grayness is something perceptual and > rivers are things recognized by our eyes and brain at a quite low level, > not so much analytical. So, if there was a way that tex could send an > paragraph shape in terms of boundingboxes to a file, and after that a > separate process could feed that into a neural net [optionally converted to > bitmaps so that the character shape could be taken into account], and the > net could send back a badness value to tex, so that there could be an > additional pass ... If such a "text picture analyzer" would work, it could handle protruding and other greyness/view related stuff as well, couldn't it? Grüßlis vom Hraban! --- http://www.planet-interkom.de/fiee.visuelle/formelsammlung.html