Ray Smith
a912967cc3
Rewrote unicharset_extractor to use the new string normalizer and read plain text as well as box files.
2017-09-08 11:49:57 +01:00
Stefan Weil
ba95a686aa
Use lept_free to free memory allocated by Leptonica
...
This fixes problems on Windows when Tesseract and Leptonica use different
C runtime libraries.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2017-07-16 08:34:18 +02:00
Justin Hotchkiss Palermo
f057938069
fix filenames in comments
2017-07-02 17:35:47 -04:00
Stefan Weil
3a67ff930e
Optimize code by replacing init_to_size with resize_no_init
...
There is no need to initialize memory with a fixed value which is
overwritten in the next step.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2017-05-12 14:34:55 +02:00
Stefan Weil
9abbc4c6f3
ccstruct: Fix wrong format string
...
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2017-05-11 19:32:51 +02:00
Raf Schietekat
3983d2f76a
Reviewed uses of reinterpret_cast
2017-05-11 01:58:40 +02:00
Ray Smith
8e79297dce
Final part of endian improvement. Adds big-endian support to lstm and fixes issue 518
2017-05-03 16:09:44 -07:00
Stefan Weil
134a253758
ccstruct: Remove unused local variable
...
This fixes a compiler warning.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2017-01-21 12:32:06 +01:00
Stefan Weil
23a7330c85
Fix page range in log message
...
The internal range is 0...(n-1), but for users a page range 1...n is
more natural. Showing a range 0...n is wrong because it would imply
n+1 pages.
Change printed text from
Loaded 72/72 pages (0-72) of document ...
to
Loaded 72/72 pages (1-72) of document ...
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2016-12-15 11:05:22 +01:00
Ray Smith
ce76d1c569
Fixes to training process to allow incremental training from a recognition model
2016-11-30 15:51:17 -08:00
Stefan Weil
120a5dbdab
Fix build for Mingw-w64
...
The old code (before commit 644469595c
)
works well with Mingw-w64 which does not support this_thread.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
2016-11-29 14:26:22 +01:00
Egor Pugin
644469595c
Fix windows build.
2016-11-24 17:32:23 +03:00
Ray Smith
5913d7344f
Added missing license headers
2016-11-18 15:53:11 -08:00
Ray Smith
f24ef67df4
Limited max height to 48 even in variable height input, enabled neural nets via ocr engine mode
2016-11-08 14:01:04 -08:00
Ray Smith
c1c1e426b3
Added new LSTM-based neural network line recognizer
2016-11-07 15:38:07 -08:00
Zdenko Podobný
27b8a5cc89
fix GRAPHICS_DISABLED build
2015-07-23 23:14:53 +02:00
Ray Smith
4a3caefd92
Add ability to build under android (without cube or scrollview).
2015-05-12 15:41:15 -07:00
theraysmith@gmail.com
d52231cff3
Started TFile conversion to remove fmemopen
...
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1138 d0cd1f9f-072b-0410-8dd7-cf729c803f20
2014-08-11 23:08:46 +00:00
theraysmith@gmail.com
fec775400d
Added ImageData class
...
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@1061 d0cd1f9f-072b-0410-8dd7-cf729c803f20
2014-04-23 22:53:16 +00:00