Superpixel-based Segmentation
Superpixels are used for segmentation of muscle fibers in multi-channel microscopy. This is a very different and more difficult problem from segmenting real world color images.
Superpixels are used for segmentation of muscle fibers in multi-channel microscopy. This is a very different and more difficult problem from segmenting real world color images.
Using the Brain Tumor Segmentation (BRATS) Benchmark, our framework achieves competitive performance when compared with other state-of-the-arts.
We propose a rule-enhanced transfer function design method that allows important structures of the volume to be more effectively separated and highlighted.
We propose to guide the volume exploration with an informative volume overview, which avoids the tedious bottom-up search of the transfer function space for regions of interest.
In this method, instead of assigning opacity directly based on voxel intensity and gradient magnitude, the opacity transfer function is automatically derived by matching the observed visibility distribution to a target visibility distribution.
Please visit my Research page for more details.