Cross Models for Twin Recognition

Nowadays, Biometrics has become a popular tool in personal identification as it can use physiological or behavioral characteristics to identify individuals. Recent advances in information technology has increased the accuracy of biometric to another level, there is still a slew of problems existed, such as complex environment, aging and unique problems. Among many classes of identifications, recognizing twins is one of the most difficult tasks as they resemble each other. This affects the use of biometrics in general cases and raises potential risks of biometrics in access control. In this paper, the authors manage to distinguish twins using four different models, namely, face recognition, ear recognition, voice recognition and lip movement recognition. Their results show that voice recognition has the best performance in twin recognition with 100% accuracy. This is much higher than that of face recognition and ear recognition (with 58% and 53% respectively); and lip movement recognition that yields 76% accuracy.