| 摘要 |
The spectral diversity of the iris can be used as a unique biometric identifier. By careful selection of a number of spectral bands, four or more, the hyper-spectral signature derived from data contained in those bands can distinguish color signatures that are not visually distinguishable in RGB color space to uniquely identify a person. Classification of hyper-spectral signatures requires less spatial resolution than the classification of texture signatures, maybe an order of magnitude or more. This reduces the size of the sensor aperture required at a given range.
|
