Segmentation of Zebrafish larvea from bright-field microscope images
This page is in support of:
An efficient and robust hybrid method for zebrafish segmentation in the bright-field microscope images
Yuanhao Guo, Zhan Xiong, and Fons J. Verbeek.
Submitted to Machine Vision and Applications, 2017
This page illustrates the segmentation method that we employ for the processing of
images from the VAST-BioImager.
2. Results from various segmentation methods for zebrafish in VAST
| Segmentation results with different methods | |
|---|---|
| A |  |
| B |  |
| C |  |
The blue bounding box indicates accurate segmentation;
The red bounding box indicates inaccurate segmentation.
(A) The segmentation obtained by the mean shift algorithm.
This method produces a whole shape representation of the zebrafish but fails in sensitivity to the edges.
(B) The segmentation obtained by the improved level set method.
This method fails to detect the transparent regions mostly found in zebrafish tail area.
(C) An accurate segmentation is obtained from a hybrid approach including the previous two methods with some refined processing.
3. Results of hybrid segmentation method for zebrafish with VAST-BioImager
The animations represent the segmentations of images with zebrafish larvae positioned in any axial-view. The axial-view images are acquired by the VAST-BioImager and a standard bright-field microscope.
| Segmentation of images with zebrafish from VAST camera | ||
|---|---|---|
| #1 | #2 | |
| 3 dpf |  |
 |
| 4 dpf |  |
 |
| 5 dpf |  |
 |
| Segmentation of images with zebrafish from microscope camera | |
|---|---|
| #1 |  |
| #2 |  |
| #3 |  |
dpf = days post fertilization, i.e. an indication of the age of the zebrafish
4. Configuration for the hybrid method
a. Spacial and color feature space window size for the mean shift algorithm:
b. Parameters for the improved level set method:
c. Parameters for the first curve evolution:
d. Parameters for the curve post refinement:
Contact Yuanhao Guo or Fons Verbeek for information.