8a36402ec0
Update haarfeatures.cpp
2015-12-07 19:01:04 +08:00
d68c392b42
calculate innTilted only for Haar::ALL mode
...
major time consuming part for training app is in function fillPassedSamples for negatives,
this change make SetImage quicker, in a test of my own data, the total time for SetImage decrease from 9177666 to 5839263,
only help for Haar feature and non Haar::ALL mode which is the most commonly case
2015-12-07 18:50:54 +08:00
07a58c47cb
Update cascadeclassifier.cpp
...
minor fix since predict() returun int
2015-12-02 17:31:17 +08:00
8562bb7092
Update cascadeclassifier.cpp
...
minor fix since predict() returun int
2015-12-02 11:50:22 +08:00
f49936a849
Fixed cmake and build issues when using Visual Studio 2015
2015-10-29 11:50:48 +03:00
d0344cd308
add checks for valid input data given to parameters
...
make the software system dependent
add LICENSE on top
2015-08-06 10:24:33 +02:00
ba7bf1ef68
add checks on input parameters for valid path and folder
...
opening a folder is system specific - made system specific code
added license
2015-08-06 10:23:41 +02:00
5cb70d34d7
fixed vector out of range exception in nextImg
2015-05-18 13:29:15 -07:00
5b3f89df0a
Merge pull request #3911 from vpisarev:core_tweaks
2015-04-07 19:03:48 +00:00
35b2139929
Basic HAL module
2015-04-07 18:16:22 +03:00
052593c760
1. Input/OutputArray optimizations;
...
2. Algorithm::load/save added (moved from StatModel)
3. copyrights updated; added copyright/licensing info for ffmpeg
4. some warnings from Xcode 6.x are fixed
2015-04-07 16:44:26 +03:00
bd2be9c79c
Merge pull request #3890 from greensea:patch-1
2015-04-07 09:33:36 +00:00
a153948a19
Merge pull request #3898 from greensea:2.4
2015-04-07 09:31:36 +00:00
7274e2ff1a
Fix a segment fault issue in cascade classfier
2015-04-07 10:38:58 +08:00
52c727f09a
Fix a segment fault issue in cascade classfier
...
work_var_count and sample_count are both 32bit integer, if the product of work_var_count and sample_count is bigger than 2^31, the compiler will treat (work_var_count*sample_count) as a negative number. Force work_var_count as an unsigned 64bit integer to avoid this issue.
2015-04-07 10:31:12 +08:00
be9c6bdd67
Merge pull request #3901 from StevenPuttemans:add_breakrule_cascade_accuracy
2015-04-03 13:24:47 +00:00
796c15d3e6
fixing wrong equation in accuracy break rule
2015-04-03 12:54:05 +02:00
e30139edc3
add the possibility to add traincascade accuracy
2015-04-03 12:47:09 +02:00
240b52151d
Merge pull request #3798 from StevenPuttemans:add_breakrule_cascade_accuracy
2015-04-03 10:19:03 +00:00
7e35f76d06
allowing people to manually define how sharp a cascade classifier model should be trained
2015-04-03 10:02:13 +02:00
ba0a8dc723
Merge pull request #3783 from StevenPuttemans:fix_traincascade_getNegatives
2015-04-01 13:56:29 +00:00
7ea0239776
Merge pull request #3835 from StevenPuttemans:upgrade_traincascade_memory_master
2015-03-24 15:19:56 +00:00
e12a04ac7e
Merge pull request #3811 from StevenPuttemans:fix_traincascade_getNegatives_master
2015-03-17 11:22:10 +00:00
d0ad599a24
update traincascade assigned memory buffers
2015-03-17 09:00:41 +01:00
4ab525c880
Merge pull request #3810 from StevenPuttemans:upgrade_traincascade_default_memory
2015-03-16 10:02:07 +00:00
2594e5e384
Merge pull request #3800 from StevenPuttemans:add_parameter_info_annotation
2015-03-12 14:29:04 +00:00
bf16f74618
fixing universal location execution
2015-03-09 13:11:29 +01:00
9f0cd9ee10
upgrade traincascade default memory
2015-03-09 10:43:14 +01:00
3419c704a9
adding usage information
2015-03-06 13:52:52 +01:00
a58bfbf3c7
info on how to use the tool
2015-03-06 13:52:02 +01:00
cdbb661eab
update cmakelists of annotation tool
2015-03-06 12:51:28 +01:00
217f628915
update cmakelists for annotation tool
2015-03-05 14:46:52 +01:00
488babf3b3
fixing undesired behaviour
2015-03-04 12:03:33 +01:00
62b8895814
Merge pull request #3654 from StevenPuttemans:add_annotation_master
2015-03-03 12:53:07 +00:00
0833352660
add annotation tool master branch
2015-02-25 11:31:50 +01:00
387a0f26fb
fix annotation tool, add auto make of tool
2015-02-25 11:27:59 +01:00
2d2ecbf3ee
Merge pull request #3653 from StevenPuttemans:add_annotationtool
2015-02-24 13:50:39 +00:00
90fb43cd11
Merge pull request #3709 from StevenPuttemans:fix_traincascade_load_message_master
2015-02-24 12:50:38 +00:00
2738939126
add same functionality as 2.4
2015-02-17 10:25:18 +01:00
f5a14e5594
fix message of preloaded parameters
2015-02-17 10:21:31 +01:00
da383e65e2
Remove deprecated methods from cv::Algorithm
2015-02-16 15:28:54 +03:00
a5a510da4b
Support for compound modules, support for contrib_world
2015-02-10 18:30:05 +03:00
f5987c258f
Fix small error in traincascade application
2015-02-03 21:32:47 +04:00
30d46313ec
adding a universal OpenCV based annotation tool for cascade classifier training
2015-01-29 13:03:28 +01:00
c48f30d4ec
Move createsamples application from 2.4 version
2014-12-10 12:17:58 +04:00
6bb6039ebb
Fixes for QNX 6.6 Neitrino support.
2014-10-23 17:17:35 +04:00
5947519ff4
Check sure that we're not already below required leaf false alarm rate before continuing to get negative samples.
2014-09-18 16:54:22 +04:00
18c0511d3c
Warning on converting int to bool fixed
2014-09-05 11:27:43 +04:00
06a1c90679
Include for cvSameImage corrected
2014-09-05 10:45:54 +04:00
d1229efeec
No output image resize in case of PNG dataset
2014-09-01 13:02:27 +04:00
Teng Cao
Maksim Shabunin
StevenPuttemans
zenev
Vadim Pisarevsky
greensea
VBystricky
vbystricky
Alexander Smorkalov
Stephen Mell
Grigory Serebryakov