摘要: Number of co-training based adaptation schemes have been proposed to address the issue biometric template representativeness intra-class variation in changing environments. However, for mobile environments remain limited. This is because devices require online labeled data and efficient management strategy due limited hardware resources. The aim this paper propose an scheme ocular biometrics. Experimental investigations on large scale VISOB dataset suggest a reduction Equal Error Rate (EER) about 25.9% biometrics environment.