Alexander Alekhin
b5d9ca9be7
text: update cmake
2016-11-29 23:26:00 +03:00
Alexander Alekhin
31d1137890
text: minor refactoring in C++ sample
2016-11-26 01:19:18 +03:00
Alexander Alekhin
1dc84e81e5
text: refactor floodfill + findContours code patterns
2016-11-26 01:07:44 +03:00
Alexander Alekhin
d632079783
text: update detectRegions()
2016-11-26 00:24:15 +03:00
Alexander Alekhin
590dc2986d
text: fix valgrind errors, minor changes
2016-11-25 18:40:18 +03:00
Vladislav Sovrasov
bedd1f763c
Replace a dummy pointer with the smart in ERStat
2016-11-18 17:17:12 +03:00
Vladislav Sovrasov
c15051611e
Fix ERFilterNM fails on some images
2016-11-11 17:03:04 +03:00
berak
c3c9723fbd
text: fix memleak in ocr_hmm_decoder
...
changed double *p to vector<double>
2016-10-12 08:56:07 +02:00
Anguelos Nicolaou
5a3c6a3354
explicit cast to int for rowRange with size_t parameters
2016-07-21 02:31:01 +02:00
Anguelos Nicolaou
5d5ec99c37
casted size_t values to std::vector<Mat>::const_iterator and fixed unreachable code in the cpp sample
2016-07-21 00:42:52 +02:00
Anguelos Nicolaou
5c526f7951
casted size_t variables to int explicitly in the construction of as Size from two size_t, also changed rangeEnd variable to a size_t
2016-07-20 22:03:18 +02:00
Anguelos Nicolaou
fc77ceab3c
Removed const from classifer data memebers to allow for assignment operator (windows 7 warned it could not create one). Created size_t temporary variables to contain integer values so that there is never math/comparissons between ints and size_t
2016-07-20 21:29:10 +02:00
Anguelos Nicolaou
bb8a51b55d
Going back before expanding ifdef HAVE_CAFFE expantion
2016-07-20 17:56:18 +02:00
Alexander Alekhin
823dea726f
migration: github.com/opencv/opencv_contrib
2016-07-12 13:02:08 +03:00
Anguelos Nicolaou
158c8a9876
fixed doxygen warning
2016-07-12 00:05:36 +02:00
Anguelos Nicolaou
d566884a6e
fixed doxygen attempt to fix IOS and visual studio warnings
2016-07-11 21:52:46 +02:00
Anguelos Nicolaou
b7a76004f6
Attenpt to supress visual studio and IOS warnings v2
2016-07-11 20:10:32 +02:00
Anguelos Nicolaou
2b788904c3
Attenpt to supress visual studio and IOS warnings
2016-07-11 19:33:17 +02:00
Alexander Alekhin
6a5f8e4a31
Merge pull request #498 from rokm:opencv_text-warning
2016-07-11 16:35:05 +00:00
Anguelos Nicolaou
53a8677664
GSOC 2016 removed warnings from example
2016-07-07 15:59:47 +02:00
Anguelos Nicolaou
7c7ecd71d2
Fixing warnings
2016-07-07 15:42:39 +02:00
Anguelos Nicolaou
551d1e684c
GSOC 2016
...
Implemented Classifier and Wordspotter as two independent classes
2016-07-06 22:27:05 +02:00
Anguelos Nicolaou
44d7339feb
Wordspotter implemented
...
Classifier implemented as an independednt class from the worspotter.
-Works both on CPU and GPU at expected top performance of 26ms per sample on a GTX 980Ti
-Simple demo for wordspoter added for cpp
-Interactiuve demo added for python
2016-07-06 16:36:23 +02:00
StevenPuttemans
dd33354fd5
fix the CMAKE order for issue #630
...
ensure that the double pass through CMakeLists.txt files do not generate double output
2016-04-18 12:34:13 +02:00
lluisgomez
f07a00cfae
remove trailing whitespace
2016-03-15 23:12:56 +01:00
lluisgomez
4092d2efe3
erGrouping python bindings and sample script textdetection.py which mimics the same detection pipeline as in textdetection.cpp
2016-03-15 22:32:31 +01:00
lluisgomez
7aedcae1ec
fix MSVS warnings
2016-01-23 10:00:55 +01:00
lluisgomez
581ae6b006
fix MSVS warnings
2016-01-23 09:24:22 +01:00
lluisgomez
9281cbfd2b
ERFilter python bindings
2016-01-22 22:29:05 +01:00
Patrick Snape
0900a86b58
Add float cast to OCR HMM
...
Required for MSVC 2008, shouldn't affect results otherwise.
2016-01-18 11:20:51 +00:00
Patrick Snape
6457fb8fff
Add float cast to OCR Beemsearch
...
Required for MSVC 2008, shouldn't affect result otherwise.
2016-01-18 11:20:51 +00:00
Rok Mandeljc
80342bccc8
opencv_text: src/erfilter.cpp: replaced bit and/or with their logical counterparts
...
Variables p2-p9 are booleans, so combination of logical negation
and use of bit and/or operations in lines 2823 and 2824 results
in the following warning from gcc:
warning: suggest parentheses around operand of ‘!’ or change ‘&’
to ‘&&’ or ‘!’ to ‘~’ [-Wparentheses]
2015-12-31 17:37:10 +01:00
previ
fe05681627
text python bindings
2015-11-06 20:00:28 +00:00
Maksim Shabunin
ac5fb1d804
Merge pull request #347 from sturkmen72:master
2015-10-22 12:45:00 +00:00
Lluis Gomez-Bigorda
c3042c3f51
remove trailing space
2015-08-26 21:47:36 +02:00
Lluis Gomez-Bigorda
a94753c0bf
fix Win x64 warning
2015-08-26 21:17:52 +02:00
Lluis Gomez-Bigorda
b19c676559
fix Win x64 and iOS warnings
2015-08-26 21:04:27 +02:00
Lluis Gomez-Bigorda
7cd6dbb0c9
Adds two more examples of croped word recognition, and show how to set the beam size parameter for small lexicon.
2015-08-26 20:13:15 +02:00
Lluis Gomez-Bigorda
cc43177675
OCRBeamSearchDecoder code refactor: fixes most of the TODOs comments, cleans-up code, and fix a bug in score_segmentation(...) member function.
2015-08-26 20:11:17 +02:00
Suleyman TURKMEN
e58699e69f
Update webcam_demo.cpp
...
fix small bug
2015-08-24 03:57:37 +03:00
Lluis Gomez-Bigorda
0be529da05
Adds demo program of Scene Text Character Recognition using the CNN classifier.
2015-08-21 18:20:41 +02:00
Lluis Gomez-Bigorda
796c26f68a
Fix w64 warnings
2015-08-03 22:15:31 +02:00
Lluis Gomez-Bigorda
1481194b54
Fix w64 warnings
2015-08-03 21:45:45 +02:00
Lluis Gomez-Bigorda
2315f9ca22
Minor bugfix: removes unwanted space character at the begining of recognition output strings.
2015-08-03 20:53:49 +02:00
Lluis Gomez-Bigorda
2538bf74a6
Adds example on segmented word recognition. Shows the use of the OCRHMMDecoder with the NM and CNN default classifiers.
2015-08-03 20:50:33 +02:00
lluis
ee677a255b
Overload the run() method in BaseOCR class in order to adapt to different classifier callbacks. The original run() method accepts only one Mat input image, this is expected to be a binarzed image with black and white text and works both with the OCRTesseract class and the OCRHMMDecoder class when the character classifier callback works with binary images (e.g. NM). The new run() method accepts two Mat input parameters. One for the gray scale (or color) source image and the other for a binary mask where each connected component corresponds to a pre-segmented character in the input image. This way the OCRHMMDecoder is able to work with character classifiers that operate in grey scale (or color) images (e.g. a CNN).
2015-08-01 13:52:24 +02:00
lluis
c146d37b93
Better CNN model for character recognition. Trained with an augmented dataset by adding translation/scale variations. Updated the croped word recognition with new class numbering (compatible with previous NM classifier).
2015-08-01 13:52:00 +02:00
Vadim Pisarevsky
f9d42886f1
Merge pull request #298 from lluisgomez:master
2015-07-31 09:44:46 +00:00
Vadim Pisarevsky
f9969b0da6
Merge pull request #308 from lluisgomez/4373
...
Fix bug #4373 :
2015-07-24 14:18:20 +03:00
lluis
43b5febc63
Fix bug #4373 : Error (Assertion failed in resize) when passing very elongated contours to the recognition module
2015-07-24 11:39:42 +02:00
