mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-03 00:49:01 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity
943 Commits 10 Branches 66 Tags 67 MiB
1d6de86150
Commit Graph

80 Commits

Author SHA1 Message Date
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
3c21c14949 Fixed issue 1245 2014-08-13 18:51:28 -07:00
Ray Smith
736d327473 NOP changes from static analysis in issue 1205 2014-08-12 16:09:12 -07:00
zdenop
ee73e3b107 fix issue 123: user-words (and user-patterns) file specified by command line 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1093 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-05-04 21:11:00 +00:00
theraysmith@gmail.com
07ca24aeaf Removed upper limit on trie size, fixing issue 1020. 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1044 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-02-03 19:18:23 +00:00
theraysmith@gmail.com
d11dc049e3 Fixed a lot of compiler/clang warnings 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1015 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-01-25 02:28:51 +00:00
theraysmith@gmail.com
60b4f8bc88 Fixed issue 743 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@978 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-01-10 18:25:46 +00:00
theraysmith@gmail.com
67f9af58b8 Removed dependence on IMAGE class 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@944 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2014-01-09 17:31:29 +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
zdenop@gmail.com
53a3e0f88a fix issue 755; add example config files from tesseract manpage 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@894 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-10-20 20:20:10 +00:00
theraysmith@gmail.com
4c3475ad2e Fixed fmemopen portability problem 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@890 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-10-10 02:07:26 +00:00
theraysmith@gmail.com
4d514d5a60 Major refactor of beam search, elimination of dead code, misc bug fixes, updates to Makefile.am, Changelog etc. 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@878 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2013-09-23 15:26:50 +00:00
david.eger@gmail.com
0aadbd0169 Save BLOB_CHOICE s for alternate choices saved during segmentation 
search so we have them when trying to replace words with alternates in
the bigram correction pass.


git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@739 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-09-01 00:33:46 +00:00
david.eger@gmail.com
4f0ff358a7 Missing close bracket. 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@714 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-29 06:15:33 +00:00
david.eger@gmail.com
4ddb3e5941 Good moming, Good aftemoon. 
During our initial chopping for each word, pay attention to whether a
dangerous ambiguity (like rn <-> m) would lead us to a dictionary word.
If so, make sure that blob gets chopped so that we can evaluate said
dictionary word during the segmentation search.

Large accuracy improvement, especially on English printed books (~9%).



git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@713 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-28 21:02:54 +00:00
david.eger@gmail.com
0d5e8b5cb6 Recording segmentation state for a choice at LogNewChoice() time was a 
bad idea -- a VIABLE_CHOICE's Blob->NumChunks can be modified as we go
by a call from Dict::LogNewSplit().  Relying on the auxilury
segmentation_state makes alt choices sometimes reference the wrong
blobs.



git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@711 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-28 20:11:57 +00:00
zdenop@gmail.com
d4d4b8aad8 improve autools system (mingw+msys fix); implementation of --disable-tessdata-prefix 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@708 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-22 20:01:33 +00:00
zdenop@gmail.com
1009a6e2f0 fopen() should use binary mode (issue 70) 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@704 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-11 12:41:17 +00:00
zdenop@gmail.com
97e19443a3 install only necessary headers, fix uninstall 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@692 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-03 13:22:51 +00:00
zdenop@gmail.com
30a70142a0 visibility - autotools part (./configure --enable-visibility) 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@690 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-03-02 23:51:33 +00:00
zdenop@gmail.com
6ccab83bd6 fixing issue 628 (replacing __MSW32__ with _WIN32) and issue 614 (reverting "class DLLSYM STRING" to "class CCUTIL_API STRING") 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@677 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-02-19 21:48:45 +00:00
david.eger@gmail.com
018f192fc2 Abolish populate_unichars(), fixing seg fault reported in Debian: 
http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=658634



git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@675 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-02-15 01:37:00 +00:00
theraysmith@gmail.com
fdd4ffe85e Fixed endian bug in dawg reader, Added word bigram correction, 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@649 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2012-02-02 02:56:18 +00:00
zdenop@gmail.com
67f47008c7 fixed "one lib" build on linux; runautoconf renamed to autogen.sh; 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@631 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-10-16 19:39:54 +00:00
joregan@gmail.com
bf4a09d72a make single/multiple libraries optional -- this needs testing!!! 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@623 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-08-29 21:28:28 +00:00
theraysmith@gmail.com
d5d15f32d7 Deleted Makefile.in from svn 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@606 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-08-18 16:32:44 +00:00
zdenop@gmail.com
9b7375edd6 MinGW portability solved + some code cleanup (based on cpplint) 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@605 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-08-15 19:28:25 +00:00
theraysmith
664b84b3c8 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@571 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-03-21 21:46:35 +00:00
theraysmith
96ca745384 Deleted lots of dead code, including PBLOB 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@565 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-03-18 22:14:53 +00:00
theraysmith
7cd3c74419 Deleted lots of dead code, including PBLOB 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@560 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2011-03-18 21:53:35 +00:00
theraysmith
b98c922391 Fixed problem with empty dawgs 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@537 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-11-30 01:04:02 +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
zdenop@gmail.com
282aa13975 *.vcproj moved to vs2008/ (bin/ and bin.dbg/ will be in vs2008/) 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@506 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-10-06 21:38:19 +00:00
zdenop@gmail.com
3964660093 update of VC++ project file to recent changes 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@495 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-09-30 21:20:00 +00:00
joregan
e0b07948fc disabling gettext checks - not currently used, and something about disabling is causing subsequent autoconf checks to not run 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@492 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-09-30 16:27:39 +00:00
joregan
9c53d54fe3 max.markin's patch for issue 345 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@477 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-09-29 23:54:18 +00:00
joregan
69f39d4bf5 fix for issue 341, thanks to max.markin 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@454 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-08-19 19:17:06 +00:00
joregan
75676cd644 doxygen 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@449 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-08-02 00:05:57 +00:00
joregan
d7924dd824 http://groups.google.com/group/tesseract-ocr/msg/16597e4f7725dfe1 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@448 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-08-01 16:24:31 +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
7e8bd73aea some casts to get rid of persistent warnings 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@435 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-21 21:19:53 +00:00
joregan
cd96d8ede5 more warnings 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@434 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-21 18:11:00 +00:00
joregan
edf7e7694c silence more useless warnings 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@432 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-21 15:11:19 +00:00
joregan
69d6d35f28 patch for issue 304 from max.markin 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@422 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-19 02:32:21 +00:00
joregan
a301f9a5c7 start of i18n 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@418 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-07-19 01:59:13 +00:00
joregan
ddcb98565a update generated autoconf/make stuff 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@369 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-05-26 14:21:37 +00:00
joregan
34d8258049 use libtool 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@368 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-05-26 14:20:20 +00:00
theraysmith
aea5be1995 Fixed issue 272 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@335 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-05-19 18:48:59 +00:00
theraysmith
f01a33ae96 Fixed issue 260 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@326 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2010-05-17 21:19:34 +00:00
theraysmith
3a13d80d24 Changes to dict for 3.00 
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@293 d0cd1f9f-072b-0410-8dd7-cf729c803f20
 2009-07-11 02:20:33 +00:00