Bonsoir
peut être en regardant par ici pour un début:
https://ressources.labomedia.org/les_pages_intelligence_artificielle_en_details#reconnaissance_d_objets_dans_des_images
François-Marie
Le 17/10/2021 à 11:32, Bernard Schoenacker a écrit :
Bonjour,
Je recherche une solution pour
Bonjour,
Je recherche une solution pour reconnaitre les images et ainsi
faciliter le classement, je sais que c'est dans l'esprit
apprentissage automatique (Machine Learning), mais je
ne sais pas par quel bout commencer à trouver l'information
Merci pour votre aimable attention
Bien à vous
I have used expensify.com at work. They have a free tier. Scanning
and an app on the phone that you just take a photo of receipts as you
go works well. If you can limit your expenses to 10 scans a month
it's free.
enpaper.work .
>
> I hope it can help you,
>
>
>
> 2017-08-23 0:22 GMT+02:00 Stephen Grant Brown <steve.brown_...@iinet.net.au>:
>> Hi All,
>> What is the best OCR package to use to scan the receipts given immediately
>> after making a purchase?
>> Yours
<j...@jretrading.com> a écrit :
> On Wed, 23 Aug 2017 08:22:37 +1000
> "Stephen Grant Brown" <steve.brown_...@iinet.net.au> wrote:
>
> > Hi All,
> > What is the best OCR package to use to scan the receipts given
> > immediately after making a purchase
Ok interesting, I will test and do feedbacks. The people I work with is
interesting for testing because blind, as myself. Then they need a good quality
OCR to read common image files. When I searched two years ago, I had not found
very accessible an performant software (gimagereader is in GTK
On Wed, 23 Aug 2017 08:22:37 +1000
"Stephen Grant Brown" <steve.brown_...@iinet.net.au> wrote:
> Hi All,
> What is the best OCR package to use to scan the receipts given
> immediately after making a purchase? Yours Sincerely
If you mean general retail receipts, are you
2017-08-23 0:22 GMT+02:00 Stephen Grant Brown <steve.brown_...@iinet.net.au>
> <steve.brown_...@iinet.net.au>:
>
> Hi All,
> What is the best OCR package to use to scan the receipts given immediately
> after making a purchase?
> Yours Sincerely
> Stephen Grant Brown
>
>
&g
Hello,
Since it may be relevant, I'm going to do some advertisement for my
own software : https://openpaper.work .
I hope it can help you,
2017-08-23 0:22 GMT+02:00 Stephen Grant Brown <steve.brown_...@iinet.net.au>:
> Hi All,
> What is the best OCR package to use to scan the re
Hi,
Many great solutions exist now for OCR on Linux.
1. Free software: gimagereader (uses Tesseract), works all right, as
well as gocr
2. Other free solution: Hypra developed Ocrizer. If you install it, you can:
- from a shortcut, running the scanning process, the characters
recognition
Probably CamScanner on a smartphone.
On 8/22/17 3:22 PM, Stephen Grant Brown wrote:
Hi All,
What is the best OCR package to use to scan the receipts given
immediately after making a purchase?
Yours Sincerely
Stephen Grant Brown
--
In theory, there is no difference between theory
On 08/22/2017 05:22 PM, Stephen Grant Brown wrote:
Hi All,
What is the best OCR package to use to scan the receipts given
immediately after making a purchase?
Yours Sincerely
Stephen Grant Brown
I wish there was a good OCR in Linux, but if there is, I don't know of
it. You need Windows
Hi All,
What is the best OCR package to use to scan the receipts given immediately
after making a purchase?
Yours Sincerely
Stephen Grant Brown
Bonjour à tous,
Je suis à la recherche d'un logiciel libre qui fasse une bonne
reconnaissance de caractères pour les partitions musicales.
J'ai vu sur wikipedia
(http://en.wikipedia.org/wiki/Category:Music_OCR_software et
http://en.wikipedia.org/wiki/Music_OCR) qu'il existe notamment les
On 01 Dec 2010, Bernd Kloss wrote:
I've found that the Debian tesseract package (tesseract-ocr-eng) works
very well, with extremely few errors.
But isn't it cli - only?
regards
It is, but is that a problem?
--
Anthony Campbell - a...@acampbell.org.uk
Microsoft-free zone - Using
Dne, 01. 12. 2010 23:57:10 je Debian TR napisal(a):
So what do you suggest? are there good commercial softwares for linux
or
should i find a win software which works under wine?
The last time I used OCR (talking about 15 years ago), it was on a
Windows machine and there was no need
On 30 Nov 2010, deloptes wrote:
Debian TR wrote:
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get it wrong, tesseract is one of the best softwares (maybe the
best
Am Mittwoch, 1. Dezember 2010 schrieb Anthony Campbell:
On 30 Nov 2010, deloptes wrote:
Debian TR wrote:
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get
Anthony Campbell wrote:
I've found that the Debian tesseract package (tesseract-ocr-eng) works
very well, with extremely few errors.
ok well I forgot to mention that usually latin chars are not a problem also
for g/jocr but it's not enough.
yes tessaract eng works fine. agree.
regards
On Tue, 2010-11-30 at 22:55 +0100, deloptes wrote:
Debian TR wrote:
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get it wrong, tesseract is one of the best softwares
On 12/01/2010 03:57 AM, Anthony Campbell wrote:
On 30 Nov 2010, deloptes wrote:
Debian TR wrote:
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get it wrong, tesseract is one
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get it wrong, tesseract is one of the best softwares (maybe the
best one)
however, in the repos (sid-squeeze) an older version
Debian TR wrote:
Hi everyone,
I am looking for a good ocr software. A quick internet search showed
that there are several softwares such as OCRad, tesseract, etc.. and if
I didn't get it wrong, tesseract is one of the best softwares (maybe the
best one)
I'm off this topic for the past 2
Hugo Vanwoerkom schrieb:
Hi,
Recently there was a post mentioning tesseract.
Turns out that is an award winning opensource OCR that works!
Hugo
I use it with the gscan2pdf frontend and it works perfectly (at least
for documents in german language)
--
To UNSUBSCRIBE, email to debian
On 21 Dec 2008, Hugo Vanwoerkom wrote:
Hi,
Recently there was a post mentioning tesseract.
Turns out that is an award winning opensource OCR that works!
I tried it out:
1. apt-get install tesseract-ocr
2. apt-get install tesseract-ocr-eng
3. use xsane to scan a page at dpi 300 and save
of the Preferences/Filetyple tab to save
in 8-bit, but glad to know this isn't needed.
export TESSDATA_PREFIX=/usr/share/tesseract-ocr/
There was no need for - l eng since I only had the English version of
tesseract installed. So to scan a page saved at 300 dpi I just do:
tesseract
did
There is an option at the top of the Preferences/Filetyple tab to save
in 8-bit, but glad to know this isn't needed.
export TESSDATA_PREFIX=/usr/share/tesseract-ocr/
There was no need for - l eng since I only had the English version of
tesseract installed. So to scan a page saved
Hi,
Recently there was a post mentioning tesseract.
Turns out that is an award winning opensource OCR that works!
I tried it out:
1. apt-get install tesseract-ocr
2. apt-get install tesseract-ocr-eng
3. use xsane to scan a page at dpi 300 and save as .tif
4. run: convert foo.tif -depth 8 foo1
2008/12/21 Hugo Vanwoerkom hvw59...@care2.com:
[3] don't scan at less than 300 dpi
And don't scan above 600 DPI!
I forget which OCR I played with a few years ago, but 300 and 600 DPI
yielded satisfactory results. 1200 DPI made things _worse_ not better,
possibly because of noise
On Sat, Dec 27, 2008 at 5:59 AM, Dotan Cohen dotanco...@gmail.com wrote:
2008/12/21 Hugo Vanwoerkom hvw59...@care2.com:
[3] don't scan at less than 300 dpi
And don't scan above 600 DPI!
I forget which OCR I played with a few years ago, but 300 and 600 DPI
yielded satisfactory results. 1200
désastreux. [...]
Pouvez me recommander un outil un peu plus adéquate à cet tâche ?
apt-get install tesseract-ocr
C'est la blague du vendredi où il y a des cas où tesseract fonctionne
?
je viens de tester un document de 3 pages scanné en pdf
convert -density 300 image.pdf image.tif
tesseract
Gaëtan PERRIER a écrit :
[...] je viens de prouver le *tesseract* français et le résultat a été
désastreux. [...]
Pouvez me recommander un outil un peu plus adéquate à cet tâche ?
apt-get install tesseract-ocr
C'est la blague du vendredi où il y a des cas où tesseract fonctionne
tesseract-ocr
C'est la blague du vendredi où il y a des cas où tesseract fonctionne ?
Il fonctionne très bien mais n'accepte que du .tif et si possible noir
et blanc
--
Daniel
--
Lisez la FAQ de la liste avant de poser une question :
http://wiki.debian.org/DebFrFrenchLists
Vous
Le vendredi 19 décembre 2008 16:09, Jacques L'helgoualc'h a écrit :
| Alain Vaugham a écrit, vendredi 19 décembre 2008, à 03:00 :
| Bonsoir la liste,
|
| bonjour,
|
| Je cherche un outil qui regarderai le contenu d'un fichier .tiff
| provenant de Hylafax et qui analyserai son contenu.
|
|
Alain Vaugham a écrit, vendredi 19 décembre 2008, à 03:00 :
Bonsoir la liste,
bonjour,
Je cherche un outil qui regarderai le contenu d'un fichier .tiff provenant
de Hylafax et qui analyserai son contenu.
Si le contenu est principalement constitué de textes - même en tableaux -
cela
Bonjour à tous,
Voici que je dois passer le OCR (Optical Character Recognition) à plusiers
documents écrits ça fait longtemps à la machine à écrire. Ce sont en
français, donc une fois convertis à pdf, je viens de prouver le *tesseract*
français et le résultat a été désastreux. La chose a pu
Le jeudi 18 décembre 2008 18:03, Sever P A a écrit :
| français et le résultat a été désastreux. La chose a pu millorer un peu en
| utilisant le *GOCR*, mais le résultat obtenu a été également
| inacceptable...
|
| Pouvez me recommander un outil un peu plus adéquate à cet tâche ?
Je n'ai pas de
Le Thu, 18 Dec 2008 23:20:17 +0100
Alain Vaugham al...@vaugham.com a écrit :
Le jeudi 18 décembre 2008 18:03, Sever P A a écrit :
| français et le résultat a été désastreux. La chose a pu millorer un peu en
| utilisant le *GOCR*, mais le résultat obtenu a été également
| inacceptable...
|
Le Thu, 18 Dec 2008 18:03:37 +0100
Sever P A gnu.se...@gmail.com a écrit:
Bonjour à tous,
Voici que je dois passer le OCR (Optical Character Recognition) à plusiers
documents écrits ça fait longtemps à la machine à écrire. Ce sont en
français, donc une fois convertis à pdf, je viens de
Bonsoir la liste,
Je cherche un outil qui regarderai le contenu d'un fichier .tiff provenant
de Hylafax et qui analyserai son contenu.
Si le contenu est principalement constitué de textes - même en tableaux -
cela signifie que c'est peut-être un fax légitime.
Si le contenu est principalement
Am 2008-07-15 00:08:45, schrieb Osamu Aoki:
Yes ... From PDF? I do not know but implimenting it is simple with some
filtering.
The OP can use netpbm to pipe the PDF through the module and then into
the ORC software...
Have a nice Day/Evening
Michelle Konzack
--
Linux-User #280138 with
hello.
Is an OCR package available for Debian 4.0, in .deb form, that can read
from PDF files, to allow text to be extracted from PDF files?
In looking at what is available in Synaptic, I could not find such a
package.
Thank you in anticipation.
--
Bret Busby
Armadale
West Australia
Hi,
On Mon, Jul 14, 2008 at 02:00:06PM +0800, Bret Busby wrote:
hello.
Is an OCR package available for Debian 4.0, in .deb form, that can read
from PDF files, to allow text to be extracted from PDF files?
Yes ... From PDF? I do not know but implimenting it is simple with some
filtering
On Mon, 14 Jul 2008, Bret Busby wrote:
hello.
Is an OCR package available for Debian 4.0, in .deb form, that can read from
PDF files, to allow text to be extracted from PDF files?
In looking at what is available in Synaptic, I could not find such a package.
Thank you in anticipation
On Tue, 15 Jul 2008 01:51:23 +0800 (WST)
Bret Busby [EMAIL PROTECTED] wrote:
Hello Bret,
So, Adobe Reader 8.0 provides the text extraction, or copying, that I
sought, so an OCR application that imports text from PDF files, is
now probably redundant (other than that it could function
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hello,...
Is there a way to run OCR application on hand written pages ?
for example Holocaust survivor pages :
http://www.yadvashem.org/wps/portal/!ut/p/_s.7_0_A/7_0_FL/.cmd/acd/.ar/sa.portlet.VictimDetailsSubmitAction/.c/6_0_9D/.ce/7_0_V9/.p
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
On 05/10/08 05:12, Jabka Atu wrote:
Hello,...
Is there a way to run OCR application on hand written pages ?
for example Holocaust survivor pages :
http://www.yadvashem.org/wps/portal/!ut/p/_s.7_0_A/7_0_FL/.cmd/acd/.ar
Jabka Atu [EMAIL PROTECTED] writes:
Is there a way to run OCR application on hand written pages ?
You can try this ocr:
http://code.google.com/p/ocropus/
http://groundstate.ca/ocr
Ocropus is the motherload of Free OCR. It began as a combination of a
handwriting analysis engine and a layout
On Sat, May 10, 2008 at 09:08:35AM -0500, Ron Johnson wrote:
GOCR might, but I *seriously* doubt it. And I doubt that any app
besides one designed for Hebrew would work.
For Hebrew there's hocr .
http://hocr.berlios.de/
Upstream has some interesting changes not included (yet?) in the
Hola a todos,
y trabaja pero lastimosamente no al 100% (siendo objetivo trabaja entre un
70-80% bien).
¿tesseract-ocr 2.01 ?
¿Qué son las características del documento de origen? ¿Problema de
instalación de tesseract?
He aquí un ejemplo con un texto en francés. El documento es vago. Es una
Gracias, voy a probarlo y les cuento.
Saludos!
--
シャカ
mbrenes.blogspot.com | sibu.homelinux.org
debian gnu/linux
Para que no se me olvide http://wiki.debian.org/Normas_Lista_Gmail
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL
2008/3/29 José Manuel (EB8CXW) [EMAIL PROTECTED]:
Hola a [EMAIL PROTECTED]:
Gracias, unas preguntas más con estos paquetes gocr y tesseract-ocr, ¿lo
qué hacer es convertir una imagen en texto elegible?, si es así, ¿cómo se
pondría en el terminar?
Podría ser así:
gocr [imagen origen
Hi,
Does anyone know OCR friendly fonts.
I am trying to print things like gnupg keys and recover it by OCR.
It has to be fixed width font.
(Experiment was done via PDF(OOffice)-graphic(Gimp). gocr was usable
but tesseract was not at first try.)
Bitstream was best but F was converted to f
Moises Brenes escribió:
2008/3/28 Manolo Díaz [EMAIL PROTECTED]:
El Sat, 29 Mar 2008 00:12:40 +
José Manuel (EB8CXW) [EMAIL PROTECTED] escribió:
Hola a [EMAIL PROTECTED]:
Desearía que me aconsejarais un programa en Debian, para escanear
texto utilizando OCR, que reconozca un
Hola a [EMAIL PROTECTED]:
Desearía que me aconsejarais un programa en Debian, para escanear texto
utilizando OCR, que reconozca un porcentaje elevado de caracteres si es
posible cerca del 100%
Gracias de antemano
--
Un saludo,
José Manuel
Gran Canaria/España
Si vas a escribir.. piensa en
El Sat, 29 Mar 2008 00:12:40 +
José Manuel (EB8CXW) [EMAIL PROTECTED] escribió:
Hola a [EMAIL PROTECTED]:
Desearía que me aconsejarais un programa en Debian, para escanear
texto utilizando OCR, que reconozca un porcentaje elevado de
caracteres si es posible cerca del 100%
Gracias de
2008/3/28 Manolo Díaz [EMAIL PROTECTED]:
El Sat, 29 Mar 2008 00:12:40 +
José Manuel (EB8CXW) [EMAIL PROTECTED] escribió:
Hola a [EMAIL PROTECTED]:
Desearía que me aconsejarais un programa en Debian, para escanear
texto utilizando OCR, que reconozca un porcentaje elevado de
Rodolfo Medina wrote:
Rodolfo Medina wrote:
I tried gocr and the result was quite miserable. Then I tried with MS
Windows
and it was almost perfect. Somewhere in the web I read that OCR software
under
Linux is very poor at the moment and that it's better to use MS Windows
Rodolfo Medina wrote:
I tried gocr and the result was quite miserable. Then I tried with MS Windows
and it was almost perfect. Somewhere in the web I read that OCR software
under
Linux is very poor at the moment and that it's better to use MS Windows for
that: unfortunately my test seems
editable text, you need OCR
software.
Andrew Sackville-West [EMAIL PROTECTED] writes:
gocr is one of a few under `apt-cache search ocr`
I tried gocr and the result was quite miserable. Then I tried with MS Windows
and it was almost perfect. Somewhere in the web I read that OCR software under
Rodolfo Medina wrote:
Somewhere in the web I read that OCR software under Linux is very
poor at the moment and that it's better to use MS Windows for that:
unfortunately my test seems to confirm that. What do you Debian
listers think?
I think you should check out these articles.
http
On Sat, Jul 21, 2007 at 08:10:27PM +0200, Bob Proulx wrote:
Rodolfo Medina wrote:
Somewhere in the web I read that OCR software under Linux is very
poor at the moment and that it's better to use MS Windows for that:
unfortunately my test seems to confirm that. What do you Debian
listers
Rodolfo Medina wrote:
I tried gocr and the result was quite miserable. Then I tried with MS Windows
and it was almost perfect. Somewhere in the web I read that OCR software
under
Linux is very poor at the moment and that it's better to use MS Windows for
that: unfortunately my test seems
suggestion please?
Why not use the Debian package? It is called tesseract-ocr.
--
Regards,| http://users.icfo.es/Florian.Kulzer
Florian |
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
On Sat, Jul 21, 2007 at 10:53:09PM +0200, Florian Kulzer wrote:
On Sat, Jul 21, 2007 at 22:25:43 +0200, Rodolfo Medina wrote:
Why not use the Debian package? It is called tesseract-ocr.
Yes. But it is old 1.02 version and has FTBFS bug.
If anyone here is interesed to help maintain update
On 7/21/07, Osamu Aoki [EMAIL PROTECTED] wrote:
On Sat, Jul 21, 2007 at 10:53:09PM +0200, Florian Kulzer wrote:
On Sat, Jul 21, 2007 at 22:25:43 +0200, Rodolfo Medina wrote:
Why not use the Debian package? It is called tesseract-ocr.
Yes. But it is old 1.02 version and has FTBFS bug.
Yes
-ocr.
Yes. But it is old 1.02 version and has FTBFS bug.
Yes, it's old. I installed from sources but I don't get the charsets.
tesseract test.tiff out
Unable to load unicharset file /usr/local/share/tessdata/eng.unicharset
How do I get them?
1. apt-cache search tesseract-ocr
tesseract
not use the Debian package? It is called tesseract-ocr.
Yes. But it is old 1.02 version and has FTBFS bug.
Yes, it's old. I installed from sources but I don't get the charsets.
tesseract test.tiff out
Unable to load unicharset file /usr/local/share/tessdata/eng.unicharset
How do I get them
If you install as stated above with aptitude, tesseract-ocr-data is
automatically installed unless you change default behavior of aptitude.
FTBFS is just package issue. This package should work. Otherwise,
please file bug report.
Osamu, thanks a lot. The package works well.
Sorry -- if I
:
On Sat, Jul 21, 2007 at 22:25:43 +0200, Rodolfo Medina wrote:
Why not use the Debian package? It is called tesseract-ocr.
Yes. But it is old 1.02 version and has FTBFS bug.
Yes, it's old. I installed from sources but I don't get the charsets.
tesseract test.tiff out
Unable to load
El jueves 7 se publicó la versión 27 de
a href=http://lem.eui.upm.es/ocre.html;ocre/a,
un ocr libre.
Es una version alfa, pero se puede probar.
Copias
a href=http://lem.eui.upm.es/ocre.html;la linea: deb ftp://lem.../a
que se indica en .../apt/sorces.list
y te bajas/instalas el ocre.deb
texte est 'cm', c'est vrai que moi même, j'ai du mal
à la lire (je trouve les déliés trop fins, aparemment gocr pense
comme moi :) ).
Les OCR préfèrent les polices et les images simples : en noir et
blanc (pas en niveaux de gris, encore moins en couleur), avec une
résolution finalement assez
Hallo,
gibt es in debian (unstable, wenns sein muss auch experimental) gute
OCR-Software? brauch garnicht so viel können, nur erstmal reinen Text,
den ich eingescannt habe, erkennen.
danke schonmal fürs lesen :)
Robert.
--
Robert Giebel [EMAIL PROTECTED]
http://www.robertgiebel.de/
http
On Sun, 21 May 2006 13:04:06 +0200 Robert Giebel
[EMAIL PROTECTED] wrote:
gibt es in debian (unstable, wenns sein muss auch experimental) gute
OCR-Software? brauch garnicht so viel können, nur erstmal reinen Text,
den ich eingescannt habe, erkennen.
Ich habe die Frage hier schonmal auf der
* Evgeni Golov [EMAIL PROTECTED] [060521 13:12]:
Ich habe die Frage hier schonmal auf der Liste gestellt und auch zwei
Antworten bekommen. Lies das hier mal durch:
http://groups.google.com/group/linux.debian.user.german/browse_thread/thread/2d28e06a7877a100/68d918567404aadb
Alles klar, das
pregunta, he estado enfocado en la búsqueda de
motores que me permitan
realizar reconocimiento OCR/ICR/OMR estoy consciente de que es
prácticamente imposible conseguir
soluciones de este estilo bajo la licencia GPL, en mi búsqueda he
logrado conseguir motores que trabajen
con OCR pero mi mayor interés
Am Sun, Dec 04, 2005 at 07:38:00PM +0100, schrieb Evgeni Golov:
N'Abend $LISTE,
mir ist grad aufgefallen, dass ich kein OCR-Tool hier auf meiner Kiste
habe. Also schnell `apt-cache search ocr` und finde in etwa folgendes:
clara - Free OCR program for Unix Systems
gocr - A command line OCR
N'Abend $LISTE,
mir ist grad aufgefallen, dass ich kein OCR-Tool hier auf meiner Kiste
habe. Also schnell `apt-cache search ocr` und finde in etwa folgendes:
clara - Free OCR program for Unix Systems
gocr - A command line OCR
kooka - scanner program for KDE
libgocr0 - API set to write your own
Also sprach Evgeni Golov [EMAIL PROTECTED] (Sun, 4 Dec 2005
19:38:00 +0100):
N'Abend $LISTE,
'abend
gocr - A command line OCR
..mit gocr-gtk (aus Etch) hab ich einige Scans probiert. Hat
eigentlich ganz gut funktioniert, _sofern_ die Schrift (sehr)
waagrecht und die Scanqualiteat (sehr) hoch
Olá!
Alguém conhece algo equivalente ao docpro para windows, disponível em
www.docpro.com.br? Na verdade imagino que ainda não haja, uma vez que
(corrijam-me se estiver errado) não há nenhum programa de OCR equivalente,
por exemplo, a um omnipage para windows. Os que já tentei (clara, gocr
* Tiago Saboga ([EMAIL PROTECTED]) wrote:
Olá!
Alguém conhece algo equivalente ao docpro para windows, disponível
em www.docpro.com.br? Na verdade imagino que ainda não haja, uma
vez que (corrijam-me se estiver errado) não há nenhum programa de
OCR equivalente, por exemplo
Bonjours
j'aurais juste aimé savoir si il été possible de faire un OCR
(reconnaissance de texte dans une image) en PHP avec des librairies
spéciales?
Sinon existe t'il des programmes permettant de le faire en ligne de
commandes?
Merci d'avance!!
--
Pensez � lire la FAQ de la liste avant de
Bonsoir,
gocr.
En php:
?php
system(gocr);
?
@+
JB
[EMAIL PROTECTED] a écrit :
Bonjours
j'aurais juste aimé savoir si il été possible de faire un OCR
(reconnaissance de texte dans une image) en PHP avec des librairies
spéciales?
Sinon existe t'il des programmes permettant de le faire
j'aurais juste aimé savoir si il été possible de faire un OCR
(reconnaissance de texte dans une image) en PHP avec des librairies
spéciales?
Sinon existe t'il des programmes permettant de le faire en ligne de
commandes?
Merci d'avance!!
--
Pensez � lire la FAQ de la
:)
[EMAIL PROTECTED] a écrit :
Bonjours
j'aurais juste aimé savoir si il été possible de faire un OCR
(reconnaissance de texte dans une image) en PHP avec des librairies
spéciales?
Sinon existe t'il des programmes permettant de le faire en ligne de
commandes?
Merci d'avance
Bonjour,
Je voulais savoir si il existe un OCR, qui fonctionne en mode consol ?
Merci !
Ptilou
On Sun, Oct 24, 2004 at 11:27:24AM +0200, philippe L wrote:
Bonjour,
Je voulais savoir si il existe un OCR, qui fonctionne en mode consol ?
Merci !
Ptilou
gocr
~$ apt-cache search gocr
gocr - A command line OCR
Nooks,
--
Pensez ? lire la FAQ de la liste avant de poser une
Hola a todos.
¿Conocéis algún OCR que sea mínimamente fiable? En Windows trabajo con
Textbridge y lo es. ¿Cómo está esta cuestión en Linux? Recordad que soy
recién llegado a Linux y me preocupa bastante esta cuestión.
Gracias anticipadas.
Segismundo
Segismundo escribió:
Hola a todos.
¿Conocéis algún OCR que sea mínimamente fiable? En Windows trabajo con
Textbridge y lo es. ¿Cómo está esta cuestión en Linux? Recordad que
soy recién llegado a Linux y me preocupa bastante esta cuestión.
Gracias anticipadas.
Segismundo
Yo uso gocr y
. However, my brutal opinion is that the quality of GOCR sucks,
and it's useless, and the closed source absolutely hands down wins the
OCR wars.
This says it all for me:
http://www.gutenberg.net/faq/S-17.shtml
Check out Scan 2, Typical Scan, and the quality of the output of GOCR
vs. the others
than you find in commercial ventures. IIRC there were a
number of tweaks one could perform in its setup, too.
The other stuff I've read said it is missing a text autostraightener.
apt-cache search straighten shows nothing.
I don't mean to gripe, but OCR accuracy went to 90% everywhere around
.
I don't mean to gripe, but OCR accuracy went to 90% everywhere around
the time the 486 came out. I'm sure GOCR can be made to do equally as
good as all the rest, but autostraightening text seems like a pretty
darn important thing.
True. Also easy for us to say, since we are not doing
brutal opinion is that the quality of GOCR sucks,
and it's useless, and the closed source absolutely hands down wins the
OCR wars.
This says it all for me:
http://www.gutenberg.net/faq/S-17.shtml
Check out Scan 2, Typical Scan, and the quality of the output of GOCR
vs. the others. (Scan 1
On Mon, Mar 08, 2004 at 03:05:28PM -0800, Number Six wrote:
...
If Gutenberg says it sucks, it sucks. Sad but true.
Again, they rock and I suck.
Sorry--I wasn't trying to say you were wrong to have an opinion about
the _software_. My point simply was that unsupported software by
nature
I've got a very clean, large font plain-jane-as-they-come book I want to
OCR. I've scanned it at grayscale and lineart at 150, 300, and 600 dpi
res, and run it through GOCR.
The output is horrible and unusable -- probably 40% of the text is
misscanned.
What up? And what can I do
On Sun, Mar 07, 2004 at 06:59:58PM -0800, Number Six wrote:
I've got a very clean, large font plain-jane-as-they-come book I want to
OCR. I've scanned it at grayscale and lineart at 150, 300, and 600 dpi
res, and run it through GOCR.
The output is horrible and unusable -- probably 40
into tif or jpg images, and them transfer
then onto my Debian Woody system for OCR processing.
I do not have a scanner so must borrow one.
My google efforts did not yield much in terms of usefull info.
Kind Regards
Dan Hunt
http://hunt.ath.cx/
adThe recent SuSE release contains
then onto my Debian Woody system for OCR processing.
I do not have a scanner so must borrow one.
My google efforts did not yield much in terms of usefull info.
Kind Regards
Dan Hunt
http://hunt.ath.cx/
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL
.
DH I could scan them into tif or jpg images, and them transfer
DH then onto my Debian Woody system for OCR processing. I do not
DH have a scanner so must borrow one.
DH My google efforts did not yield much in terms of usefull info.
Have a gander at the gocr package. --Joe
Searching for ocr at http://www.debian.org/distrib/packages gives a few
interesting hits:
gocr
gocr-gtk
gocr-tk
gocr-doc
clara
Don't know how good are, though.
You can use xsane for scanning
--
Torquil Macdonald Sørensen, http://folk.uio.no/tmac
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED
1 - 100 of 129 matches
Mail list logo