Table 1.
Methods for retinal identification.
| References | Method | Database | Performance |
|---|---|---|---|
| [12] | vascular segmentation | self-built database: 400 STARE database: 80 | recognition rate: 95% |
| [13] | vascular segmentation | Self-built database: 60 × 5 | EER (Equal Error Rate): 0.01 |
| [35] | Blood vessel skeleton | Self-built database: 200 | 38 false rejection and 0.19% recognition rejection |
| [23] | Minutiae in optical disk | Self-built database: 152 (4 × 2 and 12 × 12) | Recognition rate: 100% |
| [36] | Optical disk location C-Means clustering | Self-built database: 108 images from 27 people. | - |
| [37] | Wavelet energy feature Vessel pattern extraction | Self-built database: 40 × 10 | Recognition rate: 100% |
| [27] | Optical disk location, angular partition Angular and radial | DRIVE database: 40 | Recognition rate: 100% |
| [28] | partitioning based on vascular sketch | Self-built database: 40 × 9 | Recognition rate: 98% |
| [25] | Minutiae features from segmented vasculature. | VARIA database Self-built database: 2,063 images from 380 subjects | EER: 0 EER: 0.0153 |
| [20] | Image analysis and image statistics | Self-built database: 30 × 2 | Recognition rate: 94.5 |
| [38] | Landmarks from extracted vessel tree. | VARIA database: training 150, testing 40 × 2 | EER: 0 |