opencv_contrib

Commit Graph

Author	SHA1	Message	Date
RobertaRavanelli	fc98b871b9	Moved a cout message to avoid an error about the comunication of number of images to project	10 years ago
RobertaRavanelli	a03f3815c2	Added structured_light module	10 years ago
Vadim Pisarevsky	60f5e5ef80	Merge pull request #327 from lluisgomez:svt_dataset	10 years ago
Vadim Pisarevsky	f9dab6164c	Merge pull request #328 from lluisgomez:icdar_dataset	10 years ago
Vadim Pisarevsky	254d5b9f71	Merge pull request #344 from lluisgomez:ocr_character_recognizer	10 years ago
Lluis Gomez-Bigorda	45f4bd9828	Add benchmark code for the Chars74k dataset. Using the CNN character classifier reaches 75% and 84% accuracy for case-sensitive and case-insensitive recognition respectively.	10 years ago
Lluis Gomez-Bigorda	0be529da05	Adds demo program of Scene Text Character Recognition using the CNN classifier.	10 years ago
Kurnianggoro	a805f8baf9	add multitracker and roiselector to tracking API group	10 years ago
Vadim Pisarevsky	e18103e2e3	Merge pull request #221 from xolodilnik:fast_hough_transform	10 years ago
Maksim Shabunin	47d45c55de	ximgproc perftest	10 years ago
Maksim Shabunin	fb8d27c987	perf_line_descriptor	10 years ago
Maksim Shabunin	22e57f59e6	xfeatures2d tests	10 years ago
Patrick Snape	c8986b13fc	Complex issue around const valarray indexing Fixes https://github.com/Itseez/opencv_contrib/issues/332 Relevant material: http://stackoverflow.com/questions/6066273/pointer-into-vector-but-not-into-a-valarray http://objectmix.com/c/40001-address-first-member-valarray.html http://www.open-std.org/jtc1/sc22/wg21/docs/lwg-defects.html#389 I have to admit my naivety here, this issue is was complex for me to diagnose. It appears that in the MSVC 2008/2010 implementation of std::valarray, when indexing and assigning to a const variable, that the const version of the member function valarray<T>::operator[](size_t) returns a value instead of a const-reference. Therefore, taking the address of this is a compiler error as you can't take the address of an lvalue. By performing a const_cast on the array we change which function is called and thus we actually do recieve a const-reference. This should not effect other compilers.	10 years ago
Patrick Snape	8682d7d054	floor and ceil have no int overload on MSVC Adding float casts allows them to compile on MSVC and should not affect other compilers.	10 years ago
Patrick Snape	2b766bf091	Use std::numeric_limits<float>::quiet_NaN() NAN is a compiler specific constant that does not exist on visual studio. I also noticed that some NAN instances had been cast to float, whereas quiet_NaN is both 1) defined by the standard and 2) templated for the correct type. This is a much more portable method of getting a NaN value.	10 years ago
Patrick Snape	6a35628696	pow not overriden for integers in MSVC<2012 Just adding a float cast (since a float is being assigned to) allows MSVC to compile and should not affect other compilers.	10 years ago
Patrick Snape	d1695524d2	Add round method for daisy round does not exist in MSVC<2012 - added with the same code as in line_descritor/binary_descriptor.cpp	10 years ago
Patrick Snape	11124010aa	sqrt is not overriden for integers in MSVC<2012 Adding the decimal point means that VS doesn't complain about lack of overrides for sqrt with integers.	10 years ago
Patrick Snape	0236befcd2	Line descriptor: binary_descriptor - vector.data() vector.data() does not exist in MSVC<2012, so I changed it to &vector.front() which has the same effect (pointer to the first element in the vector).	10 years ago
Maksim Shabunin	ba49cfabff	Testing line_descriptor, reg, rgbd	10 years ago
Maksim Shabunin	95af1b58f9	Tests for xphoto	10 years ago
Maksim Shabunin	79df3dbc85	Tests for ximgproc	10 years ago
kurnianggoro	9477193a0e	Merge pull request #2 from kurnianggoro/roiselector Wrap the ROISelector class	10 years ago
Kurnianggoro	95a32d7618	new line at EOF	10 years ago
lluis	271a9b4091	Fix w64 warnings	10 years ago
lluis	6f4a09ca7e	Add benchmark for ICDAR2015 dataset using OCRTesseract and ERFilter classes. Gives word spotting f-score 0.642082 with strongly contextualized lexicon (100 words).	10 years ago
lluis	be927d962a	Report the total f1 score (0.37) and not the mean-f1. This is in accordance with the standard SVT evaluation protocol and allows for comparison with other published results.	10 years ago
lluis	769d2ada0e	Changes SVT recognition evaluation to be Case Insensitive (according to the standard evaluation protocol). This makes the benchmark obtained mean-f1 score increase from 0.23 to 0.27	10 years ago
Lluis Gomez-Bigorda	306aed4078	Adds interface for the ICDAR2015 dataset (end-to-end text recognition task)	10 years ago
Maksim Shabunin	172fdb3152	Merge pull request #303 from sbokov:improvingStereoSGBM	10 years ago
Vadim Pisarevsky	6e4d6bca75	Merge pull request #321 from lluisgomez:ocr_refactor_even	10 years ago
Lluis Gomez-Bigorda	796c26f68a	Fix w64 warnings	10 years ago
Lluis Gomez-Bigorda	1481194b54	Fix w64 warnings	10 years ago
Lluis Gomez-Bigorda	2315f9ca22	Minor bugfix: removes unwanted space character at the begining of recognition output strings.	10 years ago
Lluis Gomez-Bigorda	2538bf74a6	Adds example on segmented word recognition. Shows the use of the OCRHMMDecoder with the NM and CNN default classifiers.	10 years ago
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).	10 years ago
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).	10 years ago
sbokov	6a0545e6fe	Improving DisparityWLSFilter interface and adding a tutorial Now the filter natively supports StereoBM and StereoSGBM with no parameter tuning required. Also, now user won't need to set the ROI and the right matcher parameters manually, it is all done in the respective convenience factory method based on the left matcher instance. Tutorial was added to clarify the provided example of use.	10 years ago
Vadim Pisarevsky	f9d42886f1	Merge pull request #298 from lluisgomez:master	10 years ago
Maksim Shabunin	b63d80260b	Merge pull request #316 from StevenPuttemans:update_faceRecognizer_tutorials	10 years ago
StevenPuttemans	076f53d667	fixing facerecognizer tutorials and interface	10 years ago
Alexander Alekhin	3572007ae7	Merge pull request #304 from AlexanderStohr:master	10 years ago
Vadim Pisarevsky	f9969b0da6	Merge pull request #308 from lluisgomez/4373 Fix bug #4373:	10 years ago
Vadim Pisarevsky	2aba2d8271	Merge pull request #307 from lluisgomez/b4420 Fix memory leak bug #4420	10 years ago
lluis	43b5febc63	Fix bug #4373 : Error (Assertion failed in resize) when passing very elongated contours to the recognition module	10 years ago
lluis	015e00bcdb	Fix memory leak bug #4420	10 years ago
Alexander Alekhin	17a947d887	Merge pull request #305 from mshabunin:fix-android-warnings	10 years ago
Kurnianggoro	194455a4bd	Add: roi selector	10 years ago
Maksim Shabunin	aafda8fa66	Fixing GCC 4.9 warning	10 years ago
Alexander Stohr	70a2b23a6d	use better condition for checking if compiler supports round()	10 years ago

1 2 3 4 5 ...

1047 Commits (bf22f6f9b4dd89c1e66ca87b8cb47b21ef949209) All Branches Search

1047 Commits (bf22f6f9b4dd89c1e66ca87b8cb47b21ef949209)

All Branches