Biometric Classifier Update Using Online Learning: A Case Study in Near Infrared Face Verification

The performance of large-scale biometric system deteriorates over time as new individuals are continually enrolled. To maintain a high-level of performance, the classifier has to be retrained offline in batch mode using both the existing and new data. The process of retraining can be computationally expensive and time-consuming. This paper presents a new biometric classifier update algorithm that incrementally retrains the classifier using online learning and progressively establishes a decision hyperplane for improved classification. Each time a data is acquired, new support vectors that are linearly independent are added and existing support vectors that do not improve the classifier performance are removed.