Niblack's adaptive thresholding (Feature #4024)
| Status: | Open | Start date: | 2014-11-24 |
|---|---|---|---|
| Priority: | Low | Due date: | |
| Assignee: | Sancho McCann |
% Done: | 0% |
| Category: | imgproc, video | ||
| Target version: | 3.0 | Estimated time: | 6.00 hours |
| Difficulty: | Medium | Pull request: | https://github.com/Itseez/opencv_contrib/pull/181 |
Description
I'm interested in including Niblack's adaptive thresholding in OpenCV.
Currently, the adaptive threshold is based on the mean within a block plus an offset that is a constant parameter.
Niblack's threshold is based on the mean within a block plus an offset that is a constant parameter in [0,1] times the standard deviation of the pixel intensities within the block.
Associated revisions
Merge pull request #4024 from jet47:cuda-minmaxloc-one-row-input
History
Updated by Ilya Lavrenov over 10 years ago
Hi Sancho,
Could you implement this type of adaptive thresholding? And send us an appropriate pull request.
Thanks.
- Assignee changed from Vadim Pisarevsky to Sancho McCann
- Status changed from New to Open
- Difficulty changed from Easy to Medium
- Target version changed from 2.4.11 to 3.0
Updated by Steven Puttemans about 10 years ago
- Pull request set to https://github.com/Itseez/opencv_contrib/pull/181
Updated by Maksim Shabunin over 9 years ago
Issue has been transferred to GitHub: https://github.com/Itseez/opencv/issues/4868