mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-01-08 20:42:41 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
29,056 Commits 6 Branches 127 Tags 3 GiB
2e15582799
Commit Graph

2300 Commits

Author SHA1 Message Date
Alexander Alekhin
07729e396d imgproc(resize): avoid unnecessary type conversions 2019-12-26 00:02:52 +00:00
Alexander Alekhin
4733a19bab
Merge pull request #16194 from alalek:fix_16192 
* imgproc(test): resize(LANCZOS4) reproducer 16192

* imgproc: fix resize LANCZOS4 coefficients generation
 2019-12-19 13:20:42 +03:00
Alexander Alekhin
a8345133ac Merge pull request #16191 from terfendail:lres2c_fix 2019-12-18 22:31:52 +00:00
Vitaly Tuzov
f5a84f75c4 Fix for CV_8UC2 linear resize vectorization 2019-12-18 21:41:36 +00:00
mcellis33
5d15c65e48 Merge pull request #16136 from mcellis33:mec-nan 
* Handle det == 0 in findCircle3pts.

Issue 16051 shows a case where findCircle3pts returns NaN for the
center coordinates and radius due to dividing by a determinant of 0. In
this case, the points are colinear, so the longest distance between any
2 points is the diameter of the minimum enclosing circle.

* imgproc(test): update test checks for minEnclosingCircle()

* imgproc: fix handling of special cases in minEnclosingCircle()
 2019-12-18 17:25:59 +03:00
Paul Murphy
1c4a64f0a1 Merge pull request #16138 from pmur:reg_16137 
* imgproc: Prevent 1B overrun of 8C3 SIMD optimization

The fourth value read via v_load_q is essentially ignored,
but can cause trouble if it happens to cross page boundaries.

The final few iterations may attempt to read the most extreme
elements of S, which will read 1B beyond the array in most
aligment cases. Dynamically compute the stop. This could be
hoised from the loop, but will require a more extensive change.

Likewise, cleanup the iteration increment statements to make
it more obvious they do channel count (3) elements per pass.

This should resolve #16137

* imgproc(resize): extra check
 2019-12-12 13:00:44 +03:00
Maksim Shabunin
435c97c7a2 imgproc: add parameter checks in calcHist and calcBackProj 2019-12-10 16:10:19 +03:00
RAJKIRAN NATARAJAN
b9435b9e38 Merge pull request #16094 from saskatchewancatch:issue-16053 
* Add eps error checking for approxPolyDP to allow sensible values only
for epsilon value of Douglas-Peucker algorithm.

* Review changes for PR
 2019-12-09 22:24:35 +03:00
Paul Murphy
a011035ed6 Merge pull request #15257 from pmur:resize 
* resize: HResizeLinear reduce duplicate work

There appears to be a 2x unroll of the HResizeLinear against k,
however the k value is only incremented by 1 during the unroll. This
results in k - 1 duplicate passes when k > 1.

Likewise, the final pass may not respect the work done by the vector
loop. Start it with the offset returned by the vector op if
implemented. Note, no vector ops are implemented today.

The performance is most noticable on a linear downscale. A set of
performance tests are added to characterize this.  The performance
improvement is 10-50% depending on the scaling.

* imgproc: vectorize HResizeLinear

Performance is mostly gated by the gather operations
for x inputs.

Likewise, provide a 2x unroll against k, this reduces the
number of alpha gathers by 1/2 for larger k.

While not a 4x improvement, it still performs substantially
better under P9 for a 1.4x improvement. P8 baseline is
1.05-1.10x due to reduced VSX instruction set.

For float types, this results in a more modest
1.2x improvement.

* Update U8 processing for non-bitexact linear resize

* core: hal: vsx: improve v_load_expand_q

With a little help, we can do this quickly without gprs on
all VSX enabled targets.

* resize: Fix cn == 3 step per feedback

Per feedback, ensure we don't overrun. This was caught via the
failure observed in Test_TensorFlow.inception_accuracy.
 2019-12-09 14:54:06 +03:00
Alexander Alekhin
734de34b7a
Merge pull request #16085 from alalek:imgproc_threshold_to_zero_ipp_bug 
* imgproc(IPP): wrong result from threshold(THRESH_TOZERO)

* imgproc(IPP): disable IPP code to pass THRESH_TOZERO test
 2019-12-09 14:51:02 +03:00
Alexander Alekhin
b369c456f2 imgproc(color): clarify error message 2019-12-06 13:25:51 +03:00
Everton Constantino
75315fb297 Merge pull request #15494 from everton1984:hal_vector_get_n 
Improving VSX performance of integral function

* Adding support for vector get function on VSX datatypes so the
integral function gains a bit of performance.

* Removing get as a datatype member function and implementing a new HAL
instruction v_extract_n to get the n-th element of a vector register.

* Adding SSE/NEON/AVX intrinsics.

* Implement new HAL instruction v_broadcast_element on VSX/AVX/NEON/SSE.

* core(simd): add tests for v_extract_n/v_broadcast_element

- updated docs
- commented out code to repair compilation
- added WASM and MSA default implementations

* core(simd): fix compilation

- x86: avoid _mm256_extract_epi64/32/16/8 with MSVS 2015
- x86: _mm_extract_epi64 is 64-bit only

* cleanup
 2019-11-20 13:41:07 +03:00
clunietp
2185bce4b7 Fix 13577 2019-11-18 07:41:34 -05:00
Alexander Alekhin
f4d55d512f
imgproc: fix bit-exact GaussianBlur() / sepFilter2D() (#15855) 
* imgproc: fix bit-exact GaussianBlur() / sepFilter2D()

- avoid kernels with bad approximation
- GaussiabBlur - apply error-diffusion approximation for kernel (8-bit fraction)

* java(test): update features2d ref data

* test: update test_facedetect
 2019-11-18 01:39:27 +03:00
Alexander Alekhin
686ea5c1a6 Merge pull request #15917 from ChipKerchner:demosaicingToHal2 2019-11-16 19:45:37 +00:00
ChipKerchner
1d33335e33 Convert demosiacing with variable number of gradients to HAL - 5.5x faster 2019-11-15 07:42:03 -06:00
Alexander Alekhin
6773b938b3 Merge pull request #15896 from alalek:build_gcc_9 2019-11-14 14:22:02 +00:00
Alexander Alekhin
763b80d5fa imgproc(IPP): disable ippiDistanceTransform_3x3_8u32f_C1R 2019-11-13 14:14:19 +03:00
Alexander Alekhin
7ecdcf6ca6 build: GCC9 compilation 2019-11-12 18:49:34 +03:00
Chip Kerchner
2112aa31e6 Merge pull request #15828 from ChipKerchner:momentsToHal 
* Convert moments in tile algorithms to HAL (1.3x faster for VSX).

* Adding NEON code back in for non 64-bit platforms.

* Remove floats from post processing.
 2019-11-05 18:52:35 +03:00
Ciprian Alexandru Pitis
d2e02779c4 Merge pull request #15799 from Cpitis:feature/parallelization 
Parallelize pyrDown & calcSharrDeriv

* ::pyrDown has been parallelized

* CalcSharrDeriv parallelized

* Fixed whitespace

* Set granularity based on amount of threads enabled

* Granularity changed to cv::getNumThreads, now each thread should receive 1/n sized stripes

* imgproc: move PyrDownInvoker<CastOp>::operator() implementation

* imgproc(pyramid): remove syloopboundary()

* video: SharrDerivInvoker replace 'Mat*' => 'Mat&' fields
 2019-10-31 23:38:49 +03:00
Alexander Alekhin
bad4e5c3eb Merge pull request #15692 from alalek:core_tls_handle_thread_termination 2019-10-29 20:40:35 +00:00
Alexander Alekhin
7cf1054d36 Merge pull request #15764 from ChipKerchner:demosaicingToHal 2019-10-25 13:49:46 +00:00
Alexander Alekhin
17e2bf5717 core(tls): implement releasing of TLS on thread termination 
- move TLS & instrumentation code out of core/utility.hpp
- (*) TLSData lost .gather() method (to dispose thread data on thread termination)
- use TLSDataAccumulator for reliable collecting of thread data
- prefer using of .detachData() + .cleanupDetachedData() instead of .gather() method

(*) API is broken: replace TLSData => TLSDataAccumulator if gather required
(objects disposal on threads termination is not available in accumulator mode)
 2019-10-24 06:36:18 +00:00
ChipKerchner
c46f119e0e Convert demosaic functions to HAL 2019-10-23 10:47:07 -05:00
Everton Constantino
9ca9249992 Merge pull request #15527 from everton1984:faster_acc 
* Adding support for vectorized masking for uchar/ushort.

* Fixing bug where mask was zeroing the dst. Improved the way to calculate
the mask and tweaked for further performance improvements.

* Fixing mask comparison test.

* Restricting to one channel.

* Adding support for 3 channels, switch old approach to start using HAL's
v_select.
 2019-10-11 18:32:59 +03:00
Alexander Alekhin
4748aca61f
Merge pull request #15642 from alalek:issue_15597 2019-10-08 00:33:20 +03:00
Alexander Alekhin
f301f17b61 imgproc: accurate histogram value thresholding 2019-10-04 19:56:25 +03:00
Alexander Alekhin
c69245da1f imgproc: fix fitLine() implementation 
- update optimal solutions on each iteration
 2019-10-03 21:23:52 +00:00
Alexander Alekhin
f81e401cd0 imgproc: fix indexing issue in pyramids 
UBSAN violation expression: 'tab = tabR - x;'
 2019-09-26 18:09:47 +03:00
Vitaly Tuzov
1c17b3281a Fixed OOB reading in pyrDown 2019-09-25 13:24:17 +03:00
Vitaly Tuzov
7b3a752012 Fixed universal intrinsic undistort() implementation 2019-09-16 17:16:38 +03:00
Alexander Alekhin
e7b6753a10 imgproc: avoid manual memory allocation in connectedcomponents.cpp 2019-09-05 16:20:08 +03:00
Chip Kerchner
26228e6b4d Merge pull request #15358 from ChipKerchner:imgwarpToHal 
* Convert ImgWarp from SSE SIMD to HAL - 2.8x faster on Power (VSX) and 15% speedup on x86

* Change compile flag from CV_SIMD128 to CV_SIMD128_64F for use of v_float64x2 type

* Changing WarpPerspectiveLine from class functions and dispatching to static functions.

* Re-add dynamic runtime and dispatch execution.

* RRestore SSE4_1 optimizations inside opt_SSE4_1 namespace
 2019-08-31 13:47:58 +03:00
atinfinity
824465ea27 Merge pull request #15388 from atinfinity:impl-turbo-colormap 
Implementation of colormap "Turbo" (#15388)

* implemented turbo colormap

* add colormap image

* changed float value to avoid cast

* sorted flag check alphabetically
 2019-08-26 17:55:10 +03:00
Alexander Alekhin
29dbeb253c build: fix build with ICC 2019-08-23 16:36:32 +03:00
luz.paz
fcc7d8dd4e Fix modules/ typos 
Found using `codespell -q 3 -S ./3rdparty -L activ,amin,ang,atleast,childs,dof,endwhile,halfs,hist,iff,nd,od,uint`

backporting of commit: ec43292e1e
 2019-08-16 17:34:29 +03:00
Maksim Shabunin
6d5ac67681 Restored IPP call reduction 2019-07-31 15:41:22 +03:00
dcouwenh
d3cf0d2c06 Bayer VNG Demosaicing Fix #2 (Merge pull request #15086) 
* Update demosaicing.cpp

Fixed calculation of Bs for non-green pixels.

* Fixed cvtColor perf test for bayer VNG
 2019-07-30 23:49:46 +03:00
Vitaly Tuzov
e0f8bb83a6 Merge pull request #14994 from terfendail:wintr_undistort 
WUI based implementation to initUndistortRectifyMap (#14994)

* Add initUndistortRectifyMap performance test

* Move cv namespace boundaries

* Add wide universal intrinsics based implementation to initUndistortRectifyMap

* Dispatch undistort
 2019-07-18 19:32:51 +03:00
Chip Kerchner
c9fcc12e3b Merge pull request #15048 from ChipKerchner:reduceStoreGatheringThreshold 
* Reduce store gathering pressures - speeds thresholds by up to 20%

* Rename temporary histogram array and initialize so that MACOSX builder is happy
 2019-07-16 16:10:49 +03:00
Alexander Alekhin
054c796213 Merge pull request #15026 from terfendail:gaussian_fix 2019-07-12 18:31:09 +00:00
Vitaly Tuzov
894ad33bf4 Fix pixel value evaluation overflow in bit-exact GaussianBlur implementation 2019-07-12 18:11:51 +03:00
Alexander Alekhin
32c6e58bdb imgproc: fix unaligned memory access 
may cause crashes on ARM platform
 2019-07-11 20:49:47 +00:00
Vitaly Tuzov
82e5b961d3 Fixed initUndistortRectifyMap AVX2 implementation 2019-07-04 15:49:33 +03:00
arnaudbrejeon
a37201abee Fix crash, add assert and test 2019-07-02 09:56:31 -07:00
Vitaly Tuzov
9befb7a1d7 Merge pull request #14916 from terfendail:wsignmask_deprecated 
* Avoid using v_signmask universal intrinsic and mark it as deprecated

* Renamed v_find_negative to v_scan_forward
 2019-07-01 19:53:51 +03:00
StefanBruens
3e4a195b61 Merge pull request #14936 from StefanBruens:crosscorr_cleanup 
Crosscorr cleanup (#14936)

* Simplify code for convolution destination type/size

For the 2d filter code, destination size equals source size, and the
crossCorr function even (re-)creates the output matrix with the given size.

The number of channels also have to match. The destination type() is the
one used to create the output matrix, so we can use its type() here.

This is a preparatory patch.

Signed-off-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>

* Remove redundant destination size and type parameters from crossCorr

All calling sites of crossCorr already use (...,
mat, mat.size(), mat.type(), ...), so the parameters are redundant.

Signed-off-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>
 2019-06-30 19:04:25 +03:00
Alexander Alekhin
4112866821 Merge pull request #14886 from alalek:fix_grabcut_kmeans_call_14879 2019-06-26 20:03:04 +00:00
Alexander Alekhin
0a461e7922 Merge pull request #13252 from take1014:filter2d_13179 2019-06-26 13:34:10 +00:00
Alexander Alekhin
4a6888ccf6 imgproc: fix kmeans() call from grabCut() 2019-06-25 13:42:04 +03:00
Alexander Alekhin
5ac55fc132 core: eliminate AVX512 build warnings 
from MSVS2017 and GCC8 -O1 mode
 2019-06-20 20:00:09 +03:00
Alexander Alekhin
8ca4252303 Merge pull request #14583 from FanaticsKang:fix_undistortPoint_bug 2019-06-14 18:30:26 +00:00
Kang
549c53121a fix the bug, when k[4] is negative, icdist may be negative at the edge of image. 2019-06-14 19:00:36 +03:00
Vitaly Tuzov
d2aadabc5e Merge pull request #14743 from terfendail:wui512_fixvswarn 
Fix for MSVS2019 build warnings (#14743)

* AVX512 arch support for MSVS

* Fix for MSVS2019 build warnings: updated integral() AVX512 implementation

* Fix for MSVS2019 build warnings: reworked v_rotate_right AVX512 implementation

* fix indentation
 2019-06-11 23:07:39 +03:00
Alexander Alekhin
1e9ad5476d core(intrin): drop hasSIMD128 checks 
- use compile-time checks instead (`#if CV_SIMD128`)
- runtime checks are useless
 2019-06-08 19:20:20 +00:00
bommo1
a38157a1f4
Fix https://github.com/opencv/opencv/issues/14265 2019-06-03 23:05:03 +02:00
Vitaly Tuzov
3b015dfc7d Merge pull request #14210 from terfendail:wui_512 
AVX512 wide universal intrinsics (#14210)

* Added implementation of 512-bit wide universal intrinsics(WIP)

* Added implementation of 512-bit wide universal intrinsics: implemented WUI vector types(WIP)

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load/store

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented fp16 load/store

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented recombine and zip, implemented non-saturating and saturating arithmetics

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented bit operations

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented comparisons

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented lane shifts and reduction

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented absolute values

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented rounding and cast to float

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented LUT

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented type extension/narrowing and matrix operations

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load_deinterleave for 2 and 3 channels images

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented load_deinterleave for 2- and implemented for 4-channel images

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented store_interleave

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented signmask and checks

* Added implementation of 512-bit wide universal intrinsics(WIP): build fixes

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented popcount in case AVX512_BITALG is unavailable

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented zip

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented rotate for s8 and s16

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented interleave/deinterleave for s8 and s16

* Added implementation of 512-bit wide universal intrinsics(WIP): updated v512_set macros

* Added implementation of 512-bit wide universal intrinsics(WIP): fix for GCC wrong _mm512_abs_pd definition

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_zip to avoid AVX512_VBMI intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_invsqrt to avoid AVX512_ER intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_rotate, v_popcount and interleave/deinterleave for U8 to avoid AVX512_VBMI intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed integral image SIMD part

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed warnings

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed load_deinterleave for u8 and u16

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed v_invsqrt accuracy for f64

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave/deinterleave for u32 and u64

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave_pairs, interleave_quads and pack_triplets

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left/right, part 2

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed 512-wide universal intrinsics based resize

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed findContours by avoiding use of uint64 dependent 512-wide v_signmask()

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed trailing whitespaces

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked specific intrinsic sets dependent parts to check availability of intrinsics based on CPU feature group defines

* Added implementation of 512-bit wide universal intrinsics(WIP):Updated AVX512 implementation of v_popcount to avoid AVX512VPOPCNTDQ intrinsics if unavailable.

* Added implementation of 512-bit wide universal intrinsics(WIP): Fixed universal intrinsics data initialisation, v_mul_wrap, v_floor, v_ceil and v_signmask.

* Added implementation of 512-bit wide universal intrinsics(WIP): Removed hasSIMD512()

* Added implementation of 512-bit wide universal intrinsics(WIP): Fixes for gcc build

* Added implementation of 512-bit wide universal intrinsics(WIP): Reworked v_signmask, v_check_any() and v_check_all() implementation.
 2019-06-03 18:05:35 +03:00
Alexander Alekhin
aaf56c2839 Merge pull request #14649 from savuor:fix/luv_hls_read_oob 2019-05-27 16:24:55 +00:00
Alexander Alekhin
a81c0e6db9 Merge pull request #14447 from catree:fix_issue_14423 2019-05-27 15:00:21 +00:00
Rostislav Vasilikhin
8c698262ea rgb2hls_b: out of bounds read fixed 2019-05-27 16:19:52 +03:00
Rostislav Vasilikhin
791ebd05fc out of bounds read fixed in rgb2luv_b 2019-05-27 16:19:01 +03:00
Rostislav Vasilikhin
e07ffe902e Merge pull request #14616 from savuor:hsv_wide 
HSV and HLS color conversions rewritten to wide intrinsics (#14616)

* RGB2HSV_b vectorized

* RGB2HSV_f: widen

* RGB2HSV_f: shorten, more intuitive

* HSV2RGB_f and HSV2RGB_b widen

* hls2rgb_f widen

* instrumentation instead vx_cleanup

* RGB2HLS_f widen

* RGB2HLS_b rewritten to wide universal intrinsics

* define guard against no SIMD code

* hls2rgb_b rewritten

* extra define removed

* warning fixed

* hls2rgb_b: performance fixed
 2019-05-24 23:01:08 +03:00
catree
7ed858e38e Fix issue with solvePnPRansac and Nx3 1-channel input when the number of points is 5. Try to uniform the input shape of projectPoints and undistortPoints. 2019-05-22 14:19:16 +02:00
Rostislav Vasilikhin
e90e0ef9aa Merge pull request #14106 from savuor:lab_wide 
Lab, Luv and XYZ conversions rewritten to wide intrinsics (#14106)

* rgb2xyz<float> re-vectorized

* rgb2xyz_i vectorized for ushort and uchar

* xyz2rgb<float> vectorized

* xyz2rgb_i vectorized for both uchar and ushort

* intermediate conversions (int->float) rewritten

* packed rgb2luv rewritten

* (some) float conversions rewritten

* burnt volatile int _3 and similar

* RGB2Lab_b rewritten

* tests: logging made better

* RGB2Lab_f (LRGB path) rewritten

* Lab2RGBfloat rewritten

* Lab2RGBinteger and Lab2RGB_b rewritten to wide universal intrinsics

* Luv2RGBinteger wide vectorized

* RGB2Lab_b fixed: v_sub_wrap instead of saturated sub

* warnings fixed

* trying to fix compilation on older compilers

* using 16x8 registers for 8-element dot product

* cleanup added

* splineInterpolate: loop unrolled, perf fix for f32x4

* Lab2RGBfloat: grab 2x more data to process on f32x4

* nrepeats for Luv2RGBfloat, +20% perf

* minor

* nrepeats to RGB2Lab_f

* Lab2RGBinteger: no tab for linear BGR

* nrepeats for RGB2Luvfloat

* Luv2RGBinteger: no tab for linear RGB

* +10% more to perf of Luv2RGBfloat

* nrepeats for 256-simd for Lab2RGBfloat

* less warnings

* BOM removed

* CV_SIMD_WIDTH used for lanes number checking

* trilinearPackedInterpolate: 128-bit specialization added

* fix build; no vx_cleanup(), instrumentation instead
 2019-05-20 21:10:20 +03:00
Alexander Alekhin
30a595789c Merge pull request #14463 from thangktran:thangktran/fix-imgproc-intersectConvexConvex 2019-05-16 14:50:20 +00:00
Thang Tran
1aff378ae8 imgproc: fixed bug from intersectConvexConvex 
Added checks for all of vertices from each contour instead of checking
only for the first vertex.
 2019-05-01 11:06:30 +02:00
Alexander Alekhin
1c180f4c7f imgproc: fix RemoveOverlaps() with empty input vector 2019-04-29 21:15:23 +00:00
Brad Kelly
0fe17eeb68 Implementing AVX512 Support for 1 channel mats for CV_64F format 2019-03-22 09:44:23 -07:00
Alexander Alekhin
8c8715c4dd fix static analysis issues 2019-03-13 17:19:39 +03:00
take1014
e0b664f390 fix dftFilter2D 2019-03-13 00:27:56 +09:00
Alexander Alekhin
2c07c6718f imgproc: dispatch morph 2019-03-11 13:54:12 +00:00
Alexander Alekhin
5a01227aa1 imgproc: dispatch box_filter 2019-03-11 13:54:12 +00:00
Alexander Alekhin
ce3c92eb1f imgproc: dispatch bilateral_filter 2019-03-11 13:54:12 +00:00
Alexander Alekhin
b99c9145bf imgproc: dispatch smooth 2019-03-11 13:54:12 +00:00
Alexander Alekhin
6ec08f268f imgproc: dispatch medianBlur 2019-03-11 13:54:12 +00:00
Alexander Alekhin
8546ac3ce6 imgproc: get rid of filter.avx2.cpp 2019-03-11 13:54:12 +00:00
Alexander Alekhin
9a8dbfd57f imgproc: dispatch filter.cpp 2019-03-11 13:54:12 +00:00
Alexander Alekhin
756a98a395 imgproc: keep history of filters files 2019-03-11 13:54:07 +00:00
Alexander Alekhin
9dc7554089 imgproc: copy .dispatch.cpp 2019-03-11 13:53:59 +00:00
Alexander Alekhin
6eac8f78b9 imgproc: copy .simd.hpp 2019-03-11 13:53:59 +00:00
Alexander Alekhin
8b541e450b imgproc: dispatch color* 
Lab/XYZ modes have been postponed (color_lab.cpp):
- need to split code for tables initialization and for pixels processing first
- no significant performance improvements for switching between SSE42 / AVX2 code generation
 2019-03-07 15:45:05 +03:00
Alexander Alekhin
39783a6584 core: keep history of color*.cpp 2019-03-07 15:38:13 +03:00
Alexander Alekhin
f26912960f imgproc: clone color*.dispatch.cpp 2019-03-07 15:35:49 +03:00
Alexander Alekhin
db588bb831 imgproc: clone color*.simd.hpp 2019-03-07 15:35:13 +03:00
Vitaly Tuzov
99b39aa5bd Fixed out of bound reading in LINEAR_EXACT resize for 8UC3 2019-03-05 17:21:21 +03:00
Alexander Alekhin
3ba49ccecc imgproc: removed LSD code due original code license conflict 2019-03-01 16:25:39 +03:00
Vitaly Tuzov
9548093b46 Horizontal line processing for pyrDown() reworked using wide universal intrinsics. 2019-02-28 00:12:57 +03:00
Alexander Alekhin
1db5d82b7f Merge pull request #13844 from brad-kelly:integral_avx512_cn234 2019-02-20 12:27:16 +00:00
Vitaly Tuzov
334c4d62b5 Merge pull request #13781 from terfendail:warp_wintr 
Resize reworked using wide universal intrinsics (#13781)

* Added wide universal intrinsics optimized implementation for 3 channel bit-exact linear resize

* Reworked linear resize using new wide LUT intrinsics

* Fix for VSX intrinsics
 2019-02-20 14:30:28 +03:00
Brad Kelly
507f8add1c Implementing AVX512 Support for 2 and 4 channel mats for CV_64F format 2019-02-19 11:31:20 -08:00
Vitaly Tuzov
07c10d6fc3 Fixed out of bound reading issue in erode() and dilate() 2019-02-07 17:28:58 +03:00
Rostislav Vasilikhin
554eae56d1 Merge pull request #13708 from savuor:yuv42x_wide 
YUV42x color conversions rewritten to wide intrinsics (#13708)

* a*b+c -> fma

* YUV420sp2RGB initially vectorized

* shorter var names

* loops by 4

* yuv420p2rgb vectorized

* yuv422toRGB vectorized

* reg arrays

* rgb2yuv420 vectorized

* warnings fixed

* try to fix align error
 2019-02-01 19:09:31 +03:00
Vitaly Tuzov
2f5af1bd33 Merge pull request #13693 from terfendail:spatialgrad_wintr 
* spatialGradient() reworked to use wide universal intrinsics

* Moved row pointers inside loops
 2019-01-30 22:37:27 +03:00
Alexander Alekhin
268d73165e Merge pull request #13684 from terfendail:lblend_wintr 2019-01-29 16:21:08 +00:00
Alexander Alekhin
5916ebf500
Merge pull request #13679 from alalek:imgproc_median_blur_cleanup 
* imgproc: cleanup medianBlur_8u_O1 code

Unnecessary per-channel buffers: H[c] / lut[c]

* imgproc(medianBlur_8u_O1): use CV_SIMD_WIDTH for alignment
 2019-01-29 19:20:24 +03:00
Arnaud Brejeon
d998e70a25 Merge pull request #13672 from arnaudbrejeon:bug_fix_12961 
PyrDown: Fix bug #12961 (#13672)

* Force unaligned pointer and create test

* More cross-platform solution

* MSVC expects a proper order

* Remove useless clang macro
 2019-01-28 21:36:00 +03:00
Vitaly Tuzov
266725a378 blendLinear() reworked to use wide universal intrinsics 2019-01-25 14:16:20 +03:00
Rostislav Vasilikhin
74ba4b7ae2 fixed (un)signed packing s16 -> u8 2019-01-21 18:10:29 +03:00
Alexander Alekhin
0395b2ea9c Merge pull request #13650 from terfendail:shapedescr_wintr 2019-01-18 16:18:47 +00:00
Rostislav Vasilikhin
3812ae7949 Merge pull request #13649 from savuor:yuv_wide 
YUV/YCrCb conversions rewritten to wide intrinsics (#13649)

* YUV: minors

* YUV42x conversions template-merged

* more template-merged YUV42x conversions; some NEON code removed

* rgb2yuv<float> vectorized

* yuv2rgb<float> vectorized

* memcpy removed

* Yuv2RGB<ushort> vectorized

* unused code removed

* rgb2yuv<ushort> vectorized

* rgb2yuv<uchar> vectorized

* v_pack_u used (up to +30% perf)

* yuv2rgb<uchar> vectorized

* fixed compilation
 2019-01-18 19:06:29 +03:00
Vitaly Tuzov
a84bbc62b1 boundingRect() reworked to use wide universal intrinsics 2019-01-18 18:31:54 +03:00
Alexander Alekhin
ca00c1dce2 Merge pull request #13631 from terfendail:thresh_wintr 2019-01-16 15:45:26 +00:00
Alexander Alekhin
133eb8d13a Merge pull request #13593 from brad-kelly:integral_avx512_ver34 2019-01-15 17:47:21 +00:00
Vitaly Tuzov
a202dc9a90 threshold() reworked to use wide universal intrinsics 2019-01-15 19:15:19 +03:00
Alexander Alekhin
0e9c90a0d9 Merge pull request #13610 from terfendail:morph_wintr 2019-01-15 11:22:00 +00:00
Brad Kelly
0165ffa90d Implementing AVX512 support for 3 channel cv::integral for CV_64F 2019-01-14 16:11:01 -08:00
Vitaly Tuzov
012e43de4b Morphology reworked to use wide universal intrinsics 2019-01-14 19:02:58 +03:00
Vitaly Tuzov
ea882d58c6 Added CV_ALWAYS_INLINE macro 2019-01-11 22:40:35 +03:00
catree
d745af6763 Add Matplotlib Perceptually Uniform Sequential colormaps (viridis, plasma, inferno, magma, cividis, twilight and twilight shifted). 2019-01-06 22:48:06 +01:00
Vitaly Tuzov
7beb24553a Speedup filter2d by loop unrolling 
Added filter2d tests for 16S
 2018-12-25 14:40:48 +03:00
Alexander Alekhin
c0e11bb50e imgproc: revert "Speedup filter2d by loop unrolling" 
Commit: 124011c321
PR: https://github.com/opencv/opencv/pull/13392

Sobel filter with 16S/16U datatype is broken.
 2018-12-22 05:37:29 +00:00
Alexander Alekhin
26c5b846e6 Merge pull request #13392 from terfendail:filter_wintr 2018-12-21 11:00:44 +00:00
Vitaly Tuzov
124011c321 Speedup filter2d by loop unrolling 2018-12-20 21:18:42 +03:00
Vitaly Tuzov
131c09cf76 Fixed medianBlur implementation for hi-resolution images 2018-12-19 18:05:42 +03:00
Vitaly Tuzov
06f32e3b3e Reworked separable filter to use wide universal intrinsics 2018-12-19 17:50:09 +03:00
vishwesh5
3eb2c940de
Fix Scharr and Sobel functions 
Resolves #13375
 2018-12-17 20:39:22 +05:30
Rostislav Vasilikhin
d99a4af229 Merge pull request #13379 from savuor:color_5x5 
RGB to/from Gray rewritten to wide intrinsics (#13379)

* 5x5 to RGB added

* RGB25x5 added

* Gray2RGB added

* Gray2RGB5x5 added

* vx_set moved out of loops

* RGB5x52Gray added

* RGB2Gray written

* warnings fixed (int -> (u)short conversion)

* warning fixed

* warning fixed

* "i < n-vsize+1" to "i <= n-vsize"

* RGBA2mRGBA vectorized

* try to fix ARM builds

* fixed ARM build for RGB2RGB5x5

* mRGBA2RGBA: saturation, vectorization

* fixed CL implementation of mRGBA2RGBA (saturation added)
 2018-12-14 17:01:01 +03:00
Vitaly Tuzov
3903174f7c Merge pull request #13334 from terfendail:histogram_wintr 
* added performance test for compareHist

* compareHist reworked to use wide universal intrinsics

* Disabled vectorization for CV_COMP_CORREL and CV_COMP_BHATTACHARYYA if f64 is unsupported
 2018-12-13 14:20:22 +03:00
Alexander Alekhin
2d5ccc7b3e imgproc(resize): update checks (static analyzers) 2018-12-03 13:13:48 +03:00
Alexander Alekhin
5ed7d5a5d9 imgproc: local "CV_Assert(totalSampleCount > 0)" check 2018-11-28 20:16:37 +00:00
Alexander Alekhin
83c8214b38 eliminate build warnings 2018-11-27 15:24:59 +03:00
Alexander Alekhin
223893ea5a Merge pull request #13242 from terfendail:contours_wintr 2018-11-26 12:29:31 +00:00
Vitaly Tuzov
e1a2c034e8 Updated findContours to use wide universal intrinsics 2018-11-21 19:57:02 +03:00
Vitaly Tuzov
9ad1a84853 Unrolled bilateral filter neighbor processing loop 2018-11-16 13:51:46 +03:00
Vitaly Tuzov
f5b6bea2d4 Raised bilateralFilter processing precision for CV_32F matrices containing NaNs 2018-11-16 12:07:04 +03:00
Alexander Alekhin
1c04a5ec47 Merge pull request #12965 from terfendail:medianBlur_wintr 2018-11-16 00:47:11 +00:00
Alexander Alekhin
42742727d6 imgproc(ocl): fix morph generic filter checks 
'ksize' is not updated with 'kernel'
 2018-11-14 20:15:01 +03:00
Vitaly Tuzov
2dd98e7cc6 bilateralFilter implementation moved to separate file 2018-11-09 18:26:26 +03:00
Vitaly Tuzov
28fd967148 Updated bilateralFilter implementations to use wide universal intrinsics 2018-11-09 15:27:30 +03:00
tompollok
2da56d5af6 refactoring catching all exceptions as const ref 2018-11-08 19:59:47 +03:00
Alexander Alekhin
b74b05d1b3 Revert CV_TRY/CV_CATCH macros 
This reverts commit 7349b8f5ce (partially).
 2018-11-08 19:56:52 +03:00
Vitaly Tuzov
e5d7f446d6 Merge pull request #13056 from terfendail:box_wintr 
* Updated boxFilter implementations to use wide universal intrinsics

* boxFilter implementation moved to separate file

* Replaced ROUNDUP macro with roundUp() function
 2018-11-07 23:59:36 +03:00
Alexander Alekhin
4531f9f2f4 Merge pull request #13023 from terfendail:medianBlur_sep 2018-11-06 20:22:08 +00:00
lqy123000
cceeca3052 Merge pull request #12916 from lqy123000:bugfix_templmatch 
* avoid rounding errors

* imgproc: replace condition in matchTemplate
 2018-11-06 19:13:48 +03:00
Vitaly Tuzov
877de883b0 medianBlur() implementation moved to separate file 2018-11-02 16:28:23 +03:00
Vitaly Tuzov
0fda551dbc Updated medianBlur implementations to use wide universal intrinsics 2018-11-02 12:26:23 +03:00
Suleyman TURKMEN
4d0ed5c13c Merge pull request #12971 from sturkmen72:upd_imgproc_hpp 
* Update imgproc.hpp

* update color conversion codes
 2018-10-31 18:08:24 +03:00
Rostislav Vasilikhin
fa91d621fa Merge pull request #12876 from savuor:color_rgb2rgb_wide 
* RGB2RGB initially rewritten

* NEON impl removed

* templated version added for ushort, float

* data copying allowed for RGB2RGB

* inplace processing fixed

* fields to local vars

* no zeroupper until it's fixed

* vx_cleanup() added back
 2018-10-30 18:36:23 +03:00
maver1
e397434cb6 Merge pull request #12877 from maver1:3.4 
* Updated ICV packages and IPP integration

* core(test): minMaxIdx IPP regression test

* core(ipp): workaround minMaxIdx problem

* core(ipp): workaround meanStdDev() CV_32FC3 buffer overrun

* Returned semicolon after CV_INSTRUMENT_REGION_IPP()
 2018-10-24 15:02:53 +03:00
Michał Janiszewski
c8e6ce304f Catch exceptions by const-reference 
Exceptions caught by value incur needless cost in C++, most of them can
be caught by const-reference, especially as nearly none are actually
used. This could allow compiler generate a slightly more efficient code.
 2018-10-16 22:43:54 +02:00
Alexander Alekhin
1cc3f7abbb Merge pull request #12516 from seiko2plus:changeUnvMultiply16 2018-10-15 12:07:40 +00:00
tompollok
0b77600718 change area() emptiness checks to empty() 2018-10-13 21:35:10 +02:00
Alexander Alekhin
0d63c4c28e Merge pull request #12811 from take1014:resize_large_image 2018-10-12 16:59:25 +00:00
take1014
24af70c7e0 resolves 11283 2018-10-12 23:08:25 +09:00
Sayed Adel
9dc1d388af imgproc: Enable VSX on pyrDown & pyrUp 2018-10-11 23:03:57 +00:00
Alexander Alekhin
53785b6ac6 Merge pull request #12784 from terfendail:pyramids_wintr 2018-10-11 19:26:36 +00:00
Sayed Adel
8965f3ae06 imgproc:simd Enable VSX and wide universal intrinsics for accumulate operations 
- improve cpu dispatching calls to allow more SIMD extentions
    (SSE4.1, AVX2, VSX)
  - wide universal intrinsics
  - replace dummy v_expand with v_expand_low
  - replace v_expand + v_mul_wrap with v_mul_expand for product accumulate operations
  - use FMA for accumulate operations
  - add mask and more types to accumulate's performance tests
 2018-10-11 04:37:12 +02:00
Sayed Adel
5771fd693d Change behaviour of 16-bit multiply operator 
- redefine 16-bit multiply operator to perform saturating multiply
    instead of non-saturating multiply
  - implement 8-bit multiply operator to perform saturating multiply
  - implement v_mul_wrap() for 8-bit, 16-bit non-saturating multiply
  - improve performance of v_mul_hi() for VSX
  - update intrin tests with new changes
  - replace unv 16-bit multiplication operator with v_mul_wrap due behavior changes

  - Several improvements depend on vpisarev review

    * initial forward declarations for universal intrinsics
    * move emulating SSE intrinsics into separate file
    * implement v_mul_expand for 8-bit
    * reimplement saturating multiply using v_mul_expand + v_pack
    * map v_expand, v_load_expand, v_load_expand_q to sse4.1
    * fix overflow avx2::v_pack(uint32)
    * implement two universal intrinsics v_expand_low and v_expand_high
 2018-10-11 04:35:39 +02:00
Vitaly Tuzov
cc10e6b344 pyrDown and pyrUp SSE2 implementations replaced with wide universal intrinsics implementations 2018-10-10 21:12:47 +03:00