Applying a novelty filter as a matching criterion to Iris recognition

Currently there is an increasing demand for human-recognition systems using Iris as a pattern for representing a person's identity. A typical Iris recognition system is composed of four steps: image acquisition, iris segmentation, feature extraction and matching. This paper focuses on the matching step. Particularly, it is proposed a new method of iris matching, the Novelty Filter, tailored to compare real-valued feature vectors instead binary feature vector. The validation of the new matching measure proposed was done considering two utilization modes of the biometric system: verification mode and identification mode. According to the experimental results the novelty filter can be an exemplary technique for matching iris patterns.