mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-18 19:39:24 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity
942 Commits 10 Branches 66 Tags 221 MiB
035b324f0f
Commit Graph

36 Commits

Author SHA1 Message Date
Ray Smith
5bb0d89291 Improved debug of class pruner 2015-05-13 17:07:11 -07:00
Ray Smith
03f3c9dc88 Misc fixes missed from previous commits 2015-05-12 18:13:15 -07:00
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
Ray Smith
53fc4456cc Fixed issue 1252: Refactored LearnBlob and its call hierarchy to make it a member of Classify. 
Eliminated the flexfx scheme for calling global feature extractor functions
through an array of function pointers.
Deleted dead code I found as a by-product.
This CL does not change BlobToTrainingSample or ExtractFeatures to be full
members of Classify (the eventual goal) as that would make it even bigger,
since there are a lot of callers to these functions.
When ExtractFeatures and BlobToTrainingSample are members of Classify they
will be able to access control parameters in Classify, which will greatly
simplify developing variations to the feature extraction process.
 2015-05-12 15:22:34 -07:00
Ray Smith
25d0968d09 Major refactor to improve speed on difficut images, especially when running 
a heap checker.
SEAM and SPLIT have been begging for a refactor for a *LONG* time.
This change does most of the work of turning them into proper classes:
  Moved relevant code into SEAM/SPLIT/TBLOB/EDGEPT etc from global helper functions.
  Made the splits full data members of SEAM in an array instead of 3 separate pointers.
    This greatly reduces the amount of new/delete happening in the chopper, which is the main goal.
  Deleted redundant files: olutil.*,  makechop.*
  Brought other code into SEAM in order to keep its data members private with only priority having accessors.
 2015-05-12 14:59:14 -07:00
theraysmith@gmail.com
7f5e5264d3 Fixed issues 1093-1097 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1048 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-02-04 23:36:24 +00:00
theraysmith@gmail.com
2fcea93846 Fixed issues 1081-1090 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1046 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-02-04 02:23:18 +00:00
theraysmith@gmail.com
1a487252f4 Fixed slow-down that was caused by upping MAX_NUM_CLASSES 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1013 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-01-24 21:12:35 +00:00
zdenop
9cf08ca8d3 fix build with -DGRAPHICS_DISABLED 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@981 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-01-11 23:08:54 +00:00
zdenop
9041990be5 fix issue 1036 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@930 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-12-22 21:40:23 +00:00
zdenop
38b25b5777 fix issue 1018, 1031 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@918 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-12-06 22:07:46 +00:00
theraysmith@gmail.com
7ec4fd7a56 Refactorerd control functions to enable parallel blob classification 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@904 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-11-08 20:30:56 +00:00
theraysmith@gmail.com
99edf4ccbd Refactored classifier to make it easier to add new ones and generalized feature extractor to allow fx from grey 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@873 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-09-23 15:15:06 +00:00
theraysmith@gmail.com
da1047f020 Fixed typos and improved comments 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@753 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-09-21 15:31:20 +00:00
zdenop@gmail.com
5958f01f5f fix doxygen warnings 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@715 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-30 15:42:06 +00:00
zdenop@gmail.com
49c4ce3183 fix for GRAPHICS_DISABLED build 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@686 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-01 22:43:51 +00:00
theraysmith@gmail.com
5bc5e2a0b4 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 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@650 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-02-02 02:57:42 +00:00
theraysmith
c86a0f6892 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 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@570 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-03-21 21:45:36 +00:00
theraysmith
eba04e7c5b Fixed debug display, training on fragments 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@533 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-11-30 01:00:17 +00:00
zdenop@gmail.com
4523ce9f7d 3.01 code from http://github.com/jimregan/tesseract-ocr with addaptions related to Linux and Windows (VC2008) compile process 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@526 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-11-23 18:34:14 +00:00
joregan
f2506871f9 move include of config_auto.h to not conflict with local types. Not finished 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@490 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-09-30 15:53:40 +00:00
joregan
08defee46e more doxygen 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@450 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-08-10 19:20:11 +00:00
joregan
a18816f839 partial merge of doxygen branch (stuff without conflicts, basically) 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@441 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-27 13:23:23 +00:00
joregan
5c8ad7ee72 add config_auto.h anywhere #ifndef GRAPHICS_DISABLED is used 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@384 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-05-28 12:03:45 +00:00
theraysmith
694d3f2c20 Changes to classify for 3.00 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@291 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2009-07-11 02:17:36 +00:00
theraysmith
bea5e04b76 Fixed compilation with GRAPHICS_DISABLED 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@250 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2009-06-03 17:24:08 +00:00
theraysmith
2186613963 Fixed excessive stack use 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@241 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2009-06-02 23:34:20 +00:00
theraysmith
ff3d550c05 Removed obfuscatory 'access' macros: see issue#76 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@219 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2009-03-10 19:03:06 +00:00
theraysmith
a64f8d02dd Fixed problem with preadapted templates 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@181 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2008-08-14 22:51:39 +00:00
theraysmith
9cd87f0ec5 Fixed name collision with jpeg library 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@155 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2008-04-22 00:23:04 +00:00
theraysmith
6b5e0c4046 Made some major classifier and clustering improvements 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@130 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2008-02-01 00:07:59 +00:00
theraysmith
2f19f0c269 A minor accuracy improvement on punctuation 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@109 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2007-08-30 18:23:00 +00:00
theraysmith
2f4a43b419 Improved consistency of results from floating point calculations 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@79 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2007-07-18 00:55:02 +00:00
theraysmith
0a53f8c5bf Preparations for unicodization 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@34 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2007-05-16 01:18:59 +00:00
mezhirov
f1ce0ecd7f Changed several printfs to tprintfs to prevent stdout pollution. 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@23 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2007-04-05 10:05:50 +00:00
tmbdev
425d593ebe top-skimming import from sf.net 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk/trunk@2 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2007-03-07 20:03:40 +00:00