Path: news.mathworks.com!newsfeed-00.mathworks.com!newsfeed2.dallas1.level3.net!news.level3.com!postnews.google.com!v13g2000yqm.googlegroups.com!not-for-mail
From: Greg Heath <heath@alumni.brown.edu>
Newsgroups: comp.soft-sys.matlab
Subject: Re: MLP Optimization Problem ( generalization problem ) -- on OCR
Date: Wed, 17 Dec 2008 09:33:05 -0800 (PST)
Organization: http://groups.google.com
Lines: 24
Message-ID: <97a8f5ac-f3cb-40fa-8084-e05fcb136d2b@v13g2000yqm.googlegroups.com>
References: <ggpan0$s2d$1@fred.mathworks.com> <e9dc5bcb-cf3d-4a6f-9fdd-d4ea0b8ee6a9@d23g2000yqc.googlegroups.com> 
	<gheopa$3sq$1@fred.mathworks.com> <ghpc3g$hkd$1@fred.mathworks.com>
NNTP-Posting-Host: 68.39.98.10
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Trace: posting.google.com 1229535185 25401 127.0.0.1 (17 Dec 2008 17:33:05 GMT)
X-Complaints-To: groups-abuse@google.com
NNTP-Posting-Date: Wed, 17 Dec 2008 17:33:05 +0000 (UTC)
Complaints-To: groups-abuse@google.com
Injection-Info: v13g2000yqm.googlegroups.com; posting-host=68.39.98.10; 
	posting-account=mUealwkAAACvQrLWvunjg50tRAnsNtJR
User-Agent: G2/1.0
X-HTTP-UserAgent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 
	Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; 
	.NET CLR 2.0.50727; .NET CLR 3.0.04506.30; Seekmo 10.0.341.0),gzip(gfe),gzip(gfe)
Xref: news.mathworks.com comp.soft-sys.matlab:507573


On Dec 10, 4:25=A0pm, "zaheer ahmad" <ahmad.zah...@yah00000.com> wrote:
> well, how to train the network using different input sized matrix i.e. i =
want to first =A0train the network on 21x15 input matrix then want to train=
 ( re-train ) the same network on 16x10 input matrix. The purpose of the pr=
ocess is to get a network which will be able to recognize different size of=
 =A0characters.....

All images have to be the same size. You can try
embedding the smaller sized image into the larger
frame. However, you may need to use scale-invariant
classification.

The only method I know of (and have never used) is
to use Fourier coefficients as inputs.

You need to search for scale-invariant image
classification.

Hope this helps.

Greg

-----SNIP