Hi, Parts of the FAQ page are rather outdated, so I made some changes to it; see the attached patch.
Also, most of it applies either to v2.x or v3.x, but not both. In the interests of clarity I think it might be a good idea to split the FAQ into v2 and v3 versions. Thoughts? Nick -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
Index: FAQ.wiki =================================================================== --- FAQ.wiki (revision 737) +++ FAQ.wiki (working copy) @@ -97,12 +97,11 @@ = How do I Edit Box files used in training? = -Use bbtesseract http://code.google.com/p/bbtesseract/ or [http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3#Box_File_Editors other similar program]. +There are a variety of programs to help with this, see [http://code.google.com/p/tesseract-ocr/wiki/AddOns#Tesseract_box_editors_and_traning_tools the AddOns page]. - = How do I recognize only digits? = -*In 2.03 and above:* +== Tesseract 2.03 == Use {{{ @@ -118,9 +117,16 @@ }}} *Warning:* Until the old and new config variables get merged, you *must* have the `nobatch` parameter too. +== Tesseract 3 == + +A digits config file is already created, so just run a tesseract command like this: +{{{ +tesseract imagename outputbase digits +}}} + = How do I add just one character or one font to my favourite language, without having to retrain from scratch? = -See the TrainingTesseract wiki entry on "New! Tif/Box pairs provided!" +This is possible with Tesseract 2. See the [TrainingTesseract2] wiki entry on "New! Tif/Box pairs provided!" It is not currently possible with Tesseract 3 as Tif/Box pairs are not yet available. = Is there a Minimum Text Size? (It won't read screen text!) = @@ -142,10 +148,18 @@ = How do I provide my own dictionary? = +== Tesseract 2 == + Easy: Replace `tessdata/eng.user-words` with your own word list, in the same format - UTF8 text, one word per line. More difficult, but better for a large dictionary: Replace `tessdata/eng.word-dawg` with one created from your own word list, using wordlist2dawg. See the TrainingTesseract wiki page for details. +== Tesseract 3 == + +To add an extra word list, create a .user-words file as explained in [http://tesseract-ocr.googlecode.com/svn/trunk/doc/tesseract.1.html#_config_files_and_augmenting_with_user_data tesseract(1)]. + +If you want to replace the whole dictionary, you will need to unpack the .traineddata file, create a new word-dawg file, and then pack the files back into a .traineddata file. See TrainingTesseract3 for more details. + = wordlist2dawg doesn't work! = There is a memory problem with the 2.03 wordlist2dawg. If you don't have something more than 1GB of memory, then your system grinds to a halt and it runs very slowly. @@ -157,10 +171,8 @@ = How to increase the trust in/strength of the dictionary? = -Try upping NON_WERD and GARBAGE_STRING in dict/permute.cpp to maybe 3 or even 5. +Try increasing the variables language_model_penalty_non_freq_dict_word and language_model_penalty_non_dict_word in a config file. By default they are 0.1 and 0.15 respectively. -If the text fonts you are recognizing are significantly different from your training data, and you don't mind a slow-down, you could also try lowering ClassPrunerThreshold in classify/intmatcher.cpp to about 200 from 229. These measures should all improve the power of the dictionary to resolve words from non-words. - Of course any changes that up the power of the dictionary also up the ability to hallucinate dictionary words. If this is a problem, keep short words out of your dictionary, and don't add a vast list of words that are rarely used if they increase the number of ambiguities with more frequent words. = What are configs and how can I have more? = @@ -169,7 +181,7 @@ The other meaning is used in training and in the classifier: -A config represents a (potentially) different shape of a character from a different font. The MAX_NUM_CONFIGS limit applies to the number of different files on the command line of mftraiing containing samples of any one character, as each file is assumed to represent a different font. There is currently (2.03) a limit of 32 configs. You can get away with more than 32 files on the mftraining command line if not all the files contain all the characters. +A config represents a (potentially) different shape of a character from a different font. The MAX_NUM_CONFIGS limit applies to the number of different files on the command line of mftraining containing samples of any one character, as each file is assumed to represent a different font. There is currently (2.03) a limit of 32 configs. You can get away with more than 32 files on the mftraining command line if not all the files contain all the characters. Other ways to fix the problem: @@ -179,8 +191,7 @@ = Where is the documentation? = -There isn't much. We are concentrating on features at the moment. There is some documentation at http://tesseract-ocr.repairfaq.org/ and more at this forum thread: -http://groups.google.com/group/tesseract-ocr/browse_thread/thread/3ef5dd674cef3746/68b5f07bff0b54b2?lnk=gst&q=icdar#68b5f07bff0b54b2 +You're looking at it. If things aren't clear, search on the [http://groups.google.com/group/tesseract-ocr/ Tesseract Google Group] or ask us there. If you want to help us write more, please do, and post it to the group! = How can I try the next version? = @@ -218,4 +229,4 @@ = My question isn't in here! = -Try searching the forum: http://groups.google.com/group/tesseract-ocr as your question may have come up before even if it is not listed here. \ No newline at end of file +Try searching the forum: http://groups.google.com/group/tesseract-ocr as your question may have come up before even if it is not listed here.
