MobileRead Forums
Register Guidelines E-Books Search Today's Posts Mark Forums Read

Go Back   MobileRead Forums > Non-English Discussions > Deutsches Forum > Software
Reload this Page OCR-Software für altdeutsche Schrift

Welcome to the MobileRead Forums.

You are currently viewing our boards as a guest which gives you limited access to view most discussions and access our other features. By joining our free community today, you will have fewer ads, access to post topics, communicate privately with other members, respond to polls, upload content and access many other special features.

If you have any problems with the registration process or your account login, please contact us.

Hint: Don't have time to visit us daily? Subscribe to our main RSS feed to receive our frontpage posts at your convenience.

Notices

Software Tipps, Tools und Scripts

Reply
 
Thread Tools Search this Thread Display Modes
Old 02-17-2009, 01:35 PM   #1
mtravellerh
book creator
mtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tongue
 
mtravellerh's Avatar
 
Posts: 6,642
Karma: 22474
Join Date: Oct 2008
Location: Luxembourg
Device: PocketBook 360°, Cool-er, Ipod Touch
OCR-Software für altdeutsche Schrift
Ich möchte hier mal eine Aufruf starten, vielleicht hab ich ja Glück.

Also: Ich habe sämtliche Abenteuer des Detektiv Nobody in altdeutscher Schrift(PDF). Ich weiss. dass es von Abbyy OCR-Software gibt, die diese Schrift lesen kann, aber ich kann sie mir leider nicht leisten. Daher möchte ich gerne wissen, ob jemand diese Software hat und die PDFs durchlaufen lassen könnte (zu HTML oder TXT) Ich würde das K-Lesen übernehmen. Bitte per PM melden ode hier rein schreiben.

Falls ich niemanden finde, muss ich wohl oder übel den ganzen Text abschreiben und das wär nun wirklich sehr aufwändig.

Danke im Voraus

MTH
mtravellerh is online now   Reply With Quote
Old 02-18-2009, 05:33 AM   #2
Pulp
Palm Addict
Pulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-books
 
Pulp's Avatar
 
Posts: 475
Karma: 953
Join Date: Aug 2008
Device: Cybook Gen3 [512mb, FW: 1.5]
Vom Finereader 9 gibt's eine demo-Version.

Sie läßt sich soweit ich weiß 15 Tage nutzen und verarbeitet bis zu 50 Seiten auf einmal.

Wenn du das Ergebnis danach in HTML (oder andere Formate) exportierst (und eventuell zusammensetzt) sollte es Dir viel Zeit sparen.
Pulp is offline   Reply With Quote
Old 02-18-2009, 04:23 PM   #3
mtravellerh
book creator
mtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tongue
 
mtravellerh's Avatar
 
Posts: 6,642
Karma: 22474
Join Date: Oct 2008
Location: Luxembourg
Device: PocketBook 360°, Cool-er, Ipod Touch
Danke. Ich werd das mal probieren.
mtravellerh is online now   Reply With Quote
Old 02-18-2009, 06:10 PM   #4
netseeker
sleepless reader
netseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watch
 
netseeker's Avatar
 
Posts: 3,196
Karma: 10835
Join Date: Jan 2008
Location: Germany
Device: Sony PRS 505 (blue), iPod touch, Palm Prè, PocketBook 360° (very soon)
Tesseract ist Open Source und hat Unterstützung und Trainingsdaten sowohl für moderne deutsche Schrift als auch für die Frakturschrift:
Habs noch nicht getestet, werde das aber jetzt machen, da ich ebenfalls Bedarf am OCR von Frakturschrift habe. Wahrscheinlich werden die Ergebnisse aber schlechter wie bei Finereader & Co sein...umständlicher ist es allemal.
netseeker is online now   Reply With Quote
Old 02-18-2009, 07:42 PM   #5
netseeker
sleepless reader
netseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watch
 
netseeker's Avatar
 
Posts: 3,196
Karma: 10835
Join Date: Jan 2008
Location: Germany
Device: Sony PRS 505 (blue), iPod touch, Palm Prè, PocketBook 360° (very soon)
Habe es mit 2 verschiedenen Büchern, welche unterschiedliche Frakturschriftarten benutzen mal getestet und war ganz positiv überrascht. Naja, so positiv wie man bei einem kostenlosen OCR und dann noch mit Frakturschrift halt sein kann.

Zuerst muss man die PDF-Inhalte als tif-Grafiken bekommen, dann kann man Tesseract via
Quote:
tesseract test\nobody05_pic0005.tif testout\05 -l deu-f
damit füttern.

Anbei mal die Resultate der ersten zwei Seiten vom Detektiv Nobody 5.
Das Ergebnis der ersten Seite ist aufgrund des Drop-Cap am ersten Absatz natürlich zwangsläufig nicht so gut. Die zweite Seite sieht besser aus.

Keine Ahnung wie sich der Finereader da schlägt - vielleicht kann ja mal jemand einen Vergleich posten...
Attached Thumbnails
Click image for larger version Name: nobody05_pic0004.png Views: 187 Size: 149.8 KB ID: 23877   Click image for larger version Name: nobody05_pic0005.png Views: 171 Size: 178.4 KB ID: 23878  
Attached Files
File Type: txt 04.txt (1.4 KB, 148 views)
File Type: txt 05.txt (1.8 KB, 102 views)
netseeker is online now   Reply With Quote
Old 02-18-2009, 08:21 PM   #6
Pulp
Palm Addict
Pulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-books
 
Pulp's Avatar
 
Posts: 475
Karma: 953
Join Date: Aug 2008
Device: Cybook Gen3 [512mb, FW: 1.5]
In dem Fall solltet Ihr mal das testen: http://www.frakturschrift.de/

Der gewöhnliche Finereader bräuchte auch eine Musterdatei um brauchbare Ergebnisse zu liefern, die sollten hier schon dabei sein.
Pulp is offline   Reply With Quote
Old 02-19-2009, 04:43 AM   #7
mtravellerh
book creator
mtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tongue
 
mtravellerh's Avatar
 
Posts: 6,642
Karma: 22474
Join Date: Oct 2008
Location: Luxembourg
Device: PocketBook 360°, Cool-er, Ipod Touch
Quote:
Originally Posted by netseeker View Post
Habe es mit 2 verschiedenen Büchern, welche unterschiedliche Frakturschriftarten benutzen mal getestet und war ganz positiv überrascht. Naja, so positiv wie man bei einem kostenlosen OCR und dann noch mit Frakturschrift halt sein kann.

Zuerst muss man die PDF-Inhalte als tif-Grafiken bekommen, dann kann man Tesseract via

damit füttern.

Anbei mal die Resultate der ersten zwei Seiten vom Detektiv Nobody 5.
Das Ergebnis der ersten Seite ist aufgrund des Drop-Cap am ersten Absatz natürlich zwangsläufig nicht so gut. Die zweite Seite sieht besser aus.

Keine Ahnung wie sich der Finereader da schlägt - vielleicht kann ja mal jemand einen Vergleich posten...
Also ich find das Resultat richtig gut. Mit ein bisserl Training müsste das doch zu machen sein! Danke netseeker. Karma für Dich!
mtravellerh is online now   Reply With Quote
Old 02-19-2009, 10:13 AM   #8
netseeker
sleepless reader
netseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watchnetseeker is clearly one to watch
 
netseeker's Avatar
 
Posts: 3,196
Karma: 10835
Join Date: Jan 2008
Location: Germany
Device: Sony PRS 505 (blue), iPod touch, Palm Prè, PocketBook 360° (very soon)
Beim Trainieren von Tesseract hilft unter Windows JTesseract, eine überraschend komfortable GUI, ungemein...
Attached Thumbnails
Click image for larger version Name: jtesseract.jpg Views: 115 Size: 214.8 KB ID: 23937  
netseeker is online now   Reply With Quote
Old 02-19-2009, 01:36 PM   #9
mtravellerh
book creator
mtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tonguemtravellerh can tie a knot in a cherry stem with his or her tongue
 
mtravellerh's Avatar
 
Posts: 6,642
Karma: 22474
Join Date: Oct 2008
Location: Luxembourg
Device: PocketBook 360°, Cool-er, Ipod Touch
Danke nochmal. Bin schon fleissig am OCRen (oder wie immer das heisst). Funktioniert überraschend gut!
mtravellerh is online now   Reply With Quote
Old 02-19-2009, 03:29 PM   #10
Pulp
Palm Addict
Pulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-booksPulp has learned how to read e-books
 
Pulp's Avatar
 
Posts: 475
Karma: 953
Join Date: Aug 2008
Device: Cybook Gen3 [512mb, FW: 1.5]
optical character recognition = optische Zeichenerkennung
Pulp is offline   Reply With Quote
Reply

« Previous Thread | Next Thread »
Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes
Linear Mode Linear Mode

Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
Zeitung für nen eReader? Lorion Deutsches Forum 9 06-06-2009 05:14 PM
Bücher für Reader formatieren Stefan S. Sony Reader 1 09-11-2008 05:26 AM
OCR to use pepak Workshop 17 05-26-2008 06:30 PM
What is an OCR Cradle? JackieFrost Which one should I buy? 4 05-21-2008 09:10 PM
Why would you use OCR for a 2007 book? Barcey News and Commentary 4 11-10-2007 02:57 PM


All times are GMT -4. The time now is 12:33 PM.

Contact Us - FAQ - Guidelines - Privacy - Archive - Top

MobileRead.com is a privately owned, operated and funded community.