Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spatially coherent clustering using graph cuts
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
Snakes, shapes, and gradient vector flow
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
We present a practical graph-based algorithm for segmenting circular-shaped structures from Hoffman Modulation Contrast images of human zygotes. Hoffman Modulation Contrast is routinely used during In Vitro Fertilization procedures, and produces images with a sidelit, 3D-like appearance; our algorithm takes advantage of such peculiar appearance in order to improve the robustness of segmentation. The task is not straightforward due to the complex appearance of the objects of interest, whose image is frequently affected by defocus, clutter, debris and other artifacts. We show applications of our technique to the unsupervised segmentation of the zygote oolemma and to the subsequent supervised segmentation of its pronuclei. Experiments are provided on a number of images with different characteristics, which confirm the algorithm's robustness with respect to clutter, noise and overexposure.