Predicting ethnicity and gender from iris texture

Learning Race from Face: A Survey

“…The study of employing iris on race categorization initiated from [124], which had used Gabor feature and Adaboost selection combination on a combined iris dataset for two-races classification. Their conclusion was that iris is race-related, a result which has been further confirmed by [125], [126], [127], [128], [129], [130], all of which fit well with race recognitions (Asian/Non-Asian, Asian/Black/Cucasian). Specifically, Qiu et al [125] studied the correlation between race and iris texture and concluded that race information is illustrated in iris texture features, with best classification rate of 88.3% by SVM.…”

Iris Biometric Security Challenges and Possible Solutions: For your eyes only?Using the iris as a key

“…The iris pattern develops in utero and is fairly stable throughout the lifetime of an individual [30]. Irises are diverse in small homogeneous populations (even right and left eyes of the same subjects appear to be independent) and are believed to be largely epigenetic (not dependent on genetic information), although some correlations may be observed [31], [32]. Typically, the near-infrared (NIR) images are used, although some research into using multispectral images has been undertaken [33].…”

Beyond Recognition: The Promise of Biometric Analytics

“…Such demographic data could help reduce the search time of or act as an accuracy check on iris recognition systems, such as that used in India's Unique ID project. 6 Researchers at the University of Southampton, UK, are exploring ways to improve recognition through gait analysis (www.southampton. ac.uk/research/southamptonstories/ medhealthlife/walk_this_way.html), which thus far has largely been subjects captured in CCTV video including height, stature, position/ pose, and clothing type/color to help identify persons of interst.…”