Fusing iris and palmprint at image level for multi-biometrics verification

The phase-based image matching is effective for both iris and palm recognition tasks. Hence, we can expect that the approach may be useful for multimodal biometric system having palmprint and iris recognition capabilities. This paper investigates the fusion of palmprint and iris biometric at image level. A new image fusion algorithm named Baud limited image product (BLIP) especially for phase-based image matching is proposed. Based on this, a new multi-biometric fusion scheme at image level that combines BLIP and phase-based image matching is proposed. The effective region of iris and palm images are first extracted respectively, then they are fused into one small size image using BLIP, finally matched with the template using phase-based image matching to get a score. The experimental results show that this new scheme can not only improve the system accuracy performance, but also reduce the memory size used to store the template and time consumed by the matching.