Symbol | Description |
---|---|
General symbols | Â |
| Input color image |
| Skin class |
| Non-skin class |
P | Probability |
| Skin probability map |
| Histogram |
Σ | Covariance matrix |
| A set of blobs |
| A set of pixels in the n×n kernel around thepixel x |
δ fp | False-positive rate |
| Minimal error |
Symbols related with | Â |
the DT-based spatial analysis | Â |
(including the DSPF space) | Â |
Γ | Total path cost |
γ | Overall local cost |
γ p | Destination-probability local cost component |
γ Δ | Local cost component related with thedifference in the propagation domain |
| High-probability seed extractionthreshold |
| Lower-bound propagation threshold |
| Costless propagation threshold |
| Total path cost threshold |
| Distance in the DSPF space |
ν | Feature vector in the DSPF space |
r | Reference pixel |
P r | Reference skin probability (determinedin the neighborhood of r) |
Symbols related | Â |
with the self-adaptive | Â |
seeds method | Â |
| Initial skin seeds |
| Expanded skin seeds |
| Adapted (final) skin seeds |
t seed | Dynamic initial binarization threshold |
| Ratio of pixels used to determine t seed |
| Binarization threshold used to extract from the local skinprobability map |
| Minimum acceptable value of t seed |
| Threshold for the reference skin probability(in the dilated ) |
| Local difference costs (γ Δ ) used for buildingthe expanded |
| Local difference costs (γ Δ ) used for final‘skinness’ propagation |