Gender-From-Iris or Gender-From-Mascara?
This work addresses the reliability of biometric gender prediction for security or demographic applications, showing incremental improvements in experimental rigor.
The paper investigates gender prediction from iris texture, finding that the task is more difficult than previously reported, with accuracy significantly lower when using person-disjoint partitions and accounting for makeup effects.
Predicting a person's gender based on the iris texture has been explored by several researchers. This paper considers several dimensions of experimental work on this problem, including person-disjoint train and test, and the effect of cosmetics on eyelash occlusion and imperfect segmentation. We also consider the use of multi-layer perceptron and convolutional neural networks as classifiers, comparing the use of data-driven and hand-crafted features. Our results suggest that the gender-from-iris problem is more difficult than has so far been appreciated. Estimating accuracy using a mean of N person-disjoint train and test partitions, and considering the effect of makeup - a combination of experimental conditions not present in any previous work - we find a much weaker ability to predict gender-from-iris texture than has been suggested in previous work.