mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2025-01-18 14:41:36 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity
84920b92b3
tesseract/classify
History
Ray Smith 84920b92b3 Font and classifier output structure cleanup. 
Font recognition was poor, due to forcing a 1st and 2nd choice at
a character level, when the total score for the correct font is often
correct at the word level, so allowed the propagation of a full set
of fonts and scores to the word recognizer, which can now decide word
level fonts using the scores instead of simple votes.

Change precipitated a cleanup of output data structures for classifier
results, eliminating ScoredClass and INT_RESULT_STRUCT, with a few
extra elements going in UnicharRating, and using that wherever possible.
That added the extra complexity of 1-rating due to a flip between 0 is
good and 0 is bad for the internal classifier scores before they are
converted to rating and certainty.
2015-05-12 17:24:34 -07:00
..
adaptive.cpp Fixed issues 1093-1097 2014-02-04 23:36:24 +00:00
adaptive.h Various fixes, including memory leak in fixspace, font labels on output, removed some annoying debug output, fixes to initialization of parameters, general cleanup, and added Hindi 2011-03-21 21:45:36 +00:00
adaptmatch.cpp Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
blobclass.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
blobclass.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
classify.cpp Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
classify.h Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
cluster.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
cluster.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
clusttool.cpp Fixed some clang errors about explicit constructors and more formatting. 2014-04-28 23:10:48 +00:00
clusttool.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
cutoffs.cpp Applied patch to refix issue 331 2014-04-23 23:12:53 +00:00
cutoffs.h Changes to classify for 3.00 2009-07-11 02:17:36 +00:00
errorcounter.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
errorcounter.h Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00
featdefs.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
featdefs.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
float2int.cpp Fix segfault at ComputeNormMatch/normmatch.cpp:118 (issue 755) 2013-05-02 08:00:23 +00:00
float2int.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
fpoint.cpp Changes to classify for 3.00 2009-07-11 02:17:36 +00:00
fpoint.h 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
intfeaturedist.cpp Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
intfeaturedist.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
intfeaturemap.cpp Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
intfeaturemap.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
intfeaturespace.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
intfeaturespace.h Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
intfx.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
intfx.h Refactorerd control functions to enable parallel blob classification 2013-11-08 20:30:56 +00:00
intmatcher.cpp Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
intmatcher.h Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
intproto.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
intproto.h Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00
kdtree.cpp 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
kdtree.h 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
Makefile.am Makefile.am for fix to issue 1252 2015-05-12 15:25:00 -07:00
mastertrainer.cpp Fixed issue 1117 2014-04-24 00:52:31 +00:00
mastertrainer.h Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00
mf.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
mf.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
mfdefs.cpp top-skimming import from sf.net 2007-03-07 20:03:40 +00:00
mfdefs.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
mfoutline.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
mfoutline.h Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
mfx.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
mfx.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
normfeat.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
normfeat.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
normmatch.cpp Applied patch to refix issue 331 2014-04-23 23:12:53 +00:00
normmatch.h 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
ocrfeatures.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
ocrfeatures.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
outfeat.cpp 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
outfeat.h 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 2010-11-23 18:34:14 +00:00
picofeat.cpp Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
picofeat.h Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 2015-05-12 15:22:34 -07:00
protos.cpp Fixed slow-down that was caused by upping MAX_NUM_CLASSES 2014-01-24 21:12:35 +00:00
protos.h Fixed slow-down that was caused by upping MAX_NUM_CLASSES 2014-01-24 21:12:35 +00:00
sampleiterator.cpp Added simultaneous multi-language capability, Added support for ShapeTable in classifier and training, Refactored class pruner, Added new uniform classifier API, Added new training error counter 2012-02-02 02:57:42 +00:00
sampleiterator.h Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00
shapeclassifier.cpp fix build with -DGRAPHICS_DISABLED 2014-01-11 23:08:54 +00:00
shapeclassifier.h Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
shapetable.cpp Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
shapetable.h Font and classifier output structure cleanup. 2015-05-12 17:24:34 -07:00
tessclassifier.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
tessclassifier.h Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
trainingsample.cpp Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00
trainingsample.h Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
trainingsampleset.cpp Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 2013-09-23 15:15:06 +00:00
trainingsampleset.h Fixed a lot of compiler/clang warnings 2014-01-25 02:28:51 +00:00