4 Commits

Author	SHA1	Message	Date
Alexander Alekhin	fd09413566	Merge pull request #16731 from alalek:issue_16708 ... * imgproc(integral): avoid OOB access * imgproc(test): fix integral perf check - FP32 computation is not accurate * imgproc(integral): tune loop limits	2020-03-04 19:28:04 +00:00
Chip Kerchner	8c24af66bd	Merge pull request #16556 from ChipKerchner:vectorizeIntegralSumPixels ... * Vectorize calculating integral for line for single and multiple channels * Single vector processing for 4-channels - 25-30% faster * Single vector processing for 4-channels - 25-30% faster * Fixed AVX512 code for 4 channels * Disable 3 channel 8UC1 to 32S for SSE2 and SSE3 (slower). Use new version of 8UC1 to 64F for AVX512.	2020-02-28 19:34:06 +03:00
Alexander Alekhin	09b3383a7e	imgproc: dispatch sumpixels (integral)	2020-01-17 16:54:29 +03:00
Alexander Alekhin	4ecbcf0885	imgproc: copy sumpixels.simd.hpp	2020-01-16 15:06:34 +03:00