Performance
HALCON is implemented for highest performance, e.g., by actively exploiting
multi-core computers, SSE2 and AVX, as well as GPU acceleration.
The following runtime examples were measured using a byte image of size
640 x 480 on an Intel Core i7-2600K - 3.40 GHz computer. Note:
runtime may vary with different input data.
Shape-based matching (template size: 100 x 100, search area:
complete image with 360° rotation) |
0.875 ms |
| Affine transformation (nearest neighbor) |
0.157 ms |
| Sobel edge filter (3 x 3) |
0.089 ms |
| Median (3 x 3) |
0.111 ms |
| Binomial filter (5 x 5) |
0.078 ms |
| Gray opening (3 x 3) |
0.075 ms |
| Binary dilation (50 x 50) |
0.055 ms |
| Binary erosion (50 x 50) |
0.014 ms |
| Threshold operation |
0.061 ms |
| Subpixel-accurate threshold |
0.257 ms |
Feature calculation for 350 objects (blobs)
(features: "center of gravity" & "number of pixels") |
0.022 ms |
Subpixel-accurate measuring of edge positions
(search size 50 x 10) |
0.004 ms |
| Fast Fourier transform |
1.198 ms |