Table 1 Quality parameters used for predicting segmentation accuracy
No | Par. | Description | Indicative property |
|---|---|---|---|
1 | p x | Pupil centre x-coordinate | Close to image centre |
2 | p y | Pupil centre y-coordinate | Close to centre |
3 | p r | Pupil radius | Sensor-specific distribution (illumination) |
4 | l x | Iris centre x-coordinate | Close to centre |
5 | l y | Iris centre y-coordinate | Close to centre |
6 | l r | Iris radius | System-specific distribution (focus-distance) |
7 | a I | Iris area | System/sensor-specific distribution |
8 | c P | Pupillary contrast | Usually higher for accurate segmentation |
9 | c L | Limbic contrast | Usually higher for accurate segmentation |
10 | μ | Mean iris intensity | Difficulty of segmentation (eye colour) |
11 | σ | Iris intensity standard deviation | In-focus assessment (texture) |