Iris recognition failure over time: The effects of texture

摘要

Iris pattern is considered to be the most discriminatory of facial biometrics. However, changes in iris texture appearance occur with age, disease and medication. This study of high resolution images of 238 irides, captured with a specialised biomicroscope at three and six month intervals, and classified according to texture, measured recognition failure rates resulting from the application of local and non-local feature extraction techniques. In both local and non-local comparisons, minimum failure rates of 20.3% and 13.8% were noted, respectively. The complex fibre pattern formation of the iris results in variability in identification with differing failure rates depending on texture.