Ray Smith 0e868ef377 Major change to improve layout analysis for heavily diacritic languages: ... Tha, Vie, Kan, Tel etc. There is a new overlap detector that detects when diacritics cause a big increase in textline overlap. In such cases, diacritics from overlap regions are kept separate from layout analysis completely, allowing textline formation to happen without them. The diacritics are then assigned to 0, 1 or 2 close words at the end of layout analysis, using and modifying an old noise detection data path. The stored diacritics are used or not during recognition according to the character classifier's liking for them.		2015-05-12 16:47:02 -07:00
..
adaptions.cpp	Fixed issues 1093-1097	2014-02-04 23:36:24 +00:00
applybox.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
control.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
control.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
cube_control.cpp	Fixed issues 899/1220/1246 (mixed eng+ara)	2014-09-17 18:27:49 -07:00
cube_reco_context.cpp	Added Right-to-left/Bidi capability in the output iterators for Hebrew/Arabic, Added paragraph detection in layout analysis/post OCR, Fixed inconsistent xheight during training and over-chopping, Added simultaneous multi-language capability, Refactored top-level word recognition module, Fixed problems with internally scaled images	2012-02-02 02:59:49 +00:00
cube_reco_context.h	Misc fixes	2014-04-23 22:54:50 +00:00
cubeclassifier.cpp	Fixed issue 1102	2014-04-24 00:10:59 +00:00
cubeclassifier.h	Refactored classifier to make it easier to add new ones	2013-09-23 15:16:01 +00:00
docqual.cpp	Fixed issues 1093-1097	2014-02-04 23:36:24 +00:00
docqual.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
equationdetect.cpp	Fixed slow-down that was caused by upping MAX_NUM_CLASSES	2014-01-24 21:12:35 +00:00
equationdetect.h	Added experimental equation detector	2012-02-02 02:50:01 +00:00
fixspace.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
fixspace.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
fixxht.cpp	Fixed problems with shifted baselines so recognition can recover from layout analysis errors.	2015-05-12 15:53:45 -07:00
ltrresultiterator.cpp	Misc fixes	2014-04-23 22:54:50 +00:00
ltrresultiterator.h	Major refactor of beam search, elimination of dead code, misc bug fixes, updates to Makefile.am, Changelog etc.	2013-09-23 15:26:50 +00:00
Makefile.am	Removed dependence on IMAGE class	2014-01-09 17:48:00 +00:00
mutableiterator.h	Added Right-to-left/Bidi capability in the output iterators for Hebrew/Arabic, Added paragraph detection in layout analysis/post OCR, Fixed inconsistent xheight during training and over-chopping, Added simultaneous multi-language capability, Refactored top-level word recognition module, Fixed problems with internally scaled images	2012-02-02 02:59:49 +00:00
osdetect.cpp	Cleanup from previous changes	2014-08-12 16:12:46 -07:00
osdetect.h	Fixed issues 1081-1090	2014-02-04 02:23:18 +00:00
output.cpp	Fixed issues 1093-1097	2014-02-04 23:36:24 +00:00
output.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
pageiterator.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
pageiterator.h	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
pagesegmain.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
pagewalk.cpp	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00
par_control.cpp	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00
paragraphs_internal.h	Fixed typos and improved comments	2012-09-21 15:31:20 +00:00
paragraphs.cpp	misc fixes	2014-01-09 17:49:07 +00:00
paragraphs.h	Provide better paragraph segmentation without having to run fully	2012-05-10 00:03:34 +00:00
paramsd.cpp	Fixed issue 1099	2014-04-24 00:06:36 +00:00
paramsd.h	Add ability to build under android (without cube or scrollview).	2015-05-12 15:41:15 -07:00
pgedit.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
pgedit.h	fix svn:executable atribute, trailing spaces, version include	2013-11-03 17:24:00 +00:00
recogtraining.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
reject.cpp	Fixed issues 1093-1097	2014-02-04 23:36:24 +00:00
reject.h	Major refactor of beam search, elimination of dead code, misc bug fixes, updates to Makefile.am, Changelog etc.	2013-09-23 15:26:50 +00:00
resultiterator.cpp	fix VS2010 build;	2015-02-05 17:27:18 +01:00
resultiterator.h	fix VS2010 build;	2015-02-05 17:27:18 +01:00
superscript.cpp	Improved sub/superscript treatment	2013-09-20 19:49:47 +00:00
tessbox.cpp	Major refactor of beam search, elimination of dead code, misc bug fixes, updates to Makefile.am, Changelog etc.	2013-09-23 15:26:50 +00:00
tessbox.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
tessedit.cpp	Add ability to build under android (without cube or scrollview).	2015-05-12 15:41:15 -07:00
tessedit.h	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
tesseract_cube_combiner.cpp	Major refactor of beam search, elimination of dead code, misc bug fixes, updates to Makefile.am, Changelog etc.	2013-09-23 15:26:50 +00:00
tesseract_cube_combiner.h	fixing issue 628 (replacing __MSW32__ with _WIN32) and issue 614 (reverting "class DLLSYM STRING" to "class CCUTIL_API STRING")	2012-02-19 21:48:45 +00:00
tesseractclass.cpp	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
tesseractclass.h	Major change to improve layout analysis for heavily diacritic languages:	2015-05-12 16:47:02 -07:00
tessvars.cpp	remove unused code (Windows related)	2013-07-08 18:21:10 +00:00
tessvars.h	Removed dependence on IMAGE class	2014-01-09 17:46:37 +00:00
tfacepp.cpp	Major refactor to improve speed on difficut images, especially when running	2015-05-12 14:59:14 -07:00
thresholder.cpp	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00
thresholder.h	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00
werdit.cpp	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00
werdit.h	Major refactor of control.cpp to enable line recognition	2014-08-11 23:23:06 +00:00