This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
I don't know if temple matching is the best solution, but if it works for you and you just want to speed up the process easily, use OpenMP and run template matching on separate cores. With contemporary processors you could match up to 8 templates at a time. You can also try to use fast template matching to speed things up: http://opencv-code.com/tutorials/fast-template-matching-with-image-pyramid/ The best solution would be to optimize the template matching code to support multiple templates (I think it is planned in future releases), but it is not so easy to do.
| | 2 | No.2 Revision |
I don't know if temple matching is the best solution, but if it works for you and you just want to speed up the process easily, use OpenMP and run template matching on separate cores. With contemporary processors you could match up to 8 templates at a time. You can also try to use fast template matching to speed things up: http://opencv-code.com/tutorials/fast-template-matching-with-image-pyramid/ If you use both approaches at the same time you can expect a serious speed-up.
The best solution would be to optimize the template matching code to support multiple templates (I think it is planned in future releases), but it is not so easy to do.
