Abstract | ||
---|---|---|
Prior research has shown that the textural detail of the iris is sufficiently distinctive to distinguish identical twin siblings. However, no research has addressed the question of whether twins' irises are sufficiently similar in some sense to correctly determine that two irises are from twins. We conducted a human classification study in which participants were asked to label pairs of iris images as “twins” or “unrelated”. Participants were given three seconds to view each pair of images. We found that untrained humans can classify pairs of twins with more than 81% accuracy using the appearance of the iris alone, without any proximal image content such as eyelashes, eyelids, or tear duct visible. When expressing confident judgment, they are over 92% accurate. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/CVPRW.2010.5543237 | Computer Vision and Pattern Recognition Workshops |
Keywords | Field | DocType |
image classification,image texture,iris recognition,identical twin siblings,identical twins,image content,iris texture similarity,textural detail,biometrics,image segmentation,iris,genetics,image analysis,histograms | Iris recognition,Computer vision,Human taxonomy,Waveguide discontinuities,Pattern recognition,Computer science,Image texture,Image content,Image segmentation,Artificial intelligence,Biometrics,Contextual image classification | Conference |
Volume | Issue | ISSN |
2010 | 1 | 2160-7508 |
ISBN | Citations | PageRank |
978-1-4244-7029-7 | 7 | 0.59 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Karen Hollingsworth | 1 | 452 | 20.39 |
Kevin W. Bowyer | 2 | 11121 | 734.33 |
Patrick J. Flynn | 3 | 4405 | 307.04 |