Distinguishing identical twins by face recognition

Abstract

The paper measures the ability of face recognition algorithms to distinguish between identical twin siblings. The experimental dataset consists of images taken of 126 pairs of identical twins (252 people) collected on the same day and 24 pairs of identical twins (48 people) with images collected one year apart. In terms of both the number of paris of twins and lapsed time between acquisitions, this is the most extensive investigation of face recognition performance on twins to date. Recognition experiments are conducted using three of the top submissions to the Multiple Biometric Evaluation (MBE) 2010 Still Face Track [1]. Performance results are reported for both same day and cross year matching. Performance results are broken out by lighting conditions (studio and outside); expression (neutral and smiling); gender and age. Confidence intervals were generated by a bootstrap method. This is the most detailed covariate analysis of face recognition of twins to date.

A talking profile to distinguish identical twins

“…Unfortunately, the high similarity between identical twins is known to be a great challenge for face recognition systems. The performance of various face appearance based approaches on recognizing identical twins recently has been questioned [5], [6]. They both confirmed the difficulties encountered by appearance based face recognition systems on twin databases, and strongly suggested the need for new ways to improve performance of recognizing identical twins.…”

“…This conclusion verifies the observation that parents of twins prefer to use the motion of their children for recognition. The proposal in this work presents a new way to recognize identical twins, as suggested in the previous research [5], [6], [11].…”

“…To our best knowledge, there are limited works on identical twin recognition using 2D face biometric [5], [6], [11]. Sun et al [5] were the first to evaluate the performance of appearance based face recognition to distinguish between twins.…”

“…Based on their experimental results the best performance was observed under ideal conditions (same day, studio lighting and neutral expression), and under more realistic conditions, distinguishing between identical twins was very challenging. Klare et.al [11] analyzed the features of each facial component to distinguish identical twins from the same database in [6]. They also analyzed the possibility of using facial marks to distinguish identical twins.…”

“…Experiments were conducted using the FaceVACS commercial matcher and showed that identical twins are a challenge to current face recognition systems. Phillips et.al [6] thoroughly extended the analysis of the performance of face recognition systems in distinguishing 1 This is the largest video database of identical twins, known to authors between identical twins on another database collected at the Twins Days festival in Ohio in 2009 and 2010. It consisted of images of 126 pairs of identical twins collected on the same day and 24 pairs with images collected one year apart.…”