FIGURE
Fig. 2
- ID
- ZDB-FIG-180516-31
- Publication
- Vandaele et al., 2018 - Landmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach
- Other Figures
- All Figure Page
- Back to All Figure Page
Fig. 2
On the left, illustration of multi-resolution features representing one pixel (on the DROSO dataset, with D = 6 windows). The corresponding described pixel is located at the center of the windows (in blue). On the right, illustration of R and R max radius (on the ZEBRA dataset). Observations in the R radius are considered as landmarks (positive) for the classification approach. At training, PπR2 non-landmark observations are extracted in the [R, R max ] radius. |
Expression Data
Expression Detail
Antibody Labeling
Phenotype Data
Phenotype Detail
Acknowledgments
This image is the copyrighted work of the attributed author or publisher, and
ZFIN has permission only to display this image to its users.
Additional permissions should be obtained from the applicable author or publisher of the image.
Full text @ Sci. Rep.