Multimodal Biometric Recognition Based on 3D Ultrasound Palmprint-Hand Geometry Fusion

In recent years, multimodal biometric systems are increasingly employed in many application field due to several advantages terms of universality, recognition rate. and security. Among various acquisition technologies, Ultrasound shows important merits, because it allows obtaining volumetric images the human body hence a more accurate description characteristics verify liveness. this work, ultrasound system based on fusion between 3D hand geometry palmprint features is proposed experimentally evaluated. The acquires image whole for both characteristics, 2D extracted at different depth levels. From each image, then properly combined achieve template. Recognition performances evaluated through verification identification experiments by employing homemade database. Experiments carried out first two unimodal biometrics successively, fusing modalities score level. Results have shown that able dramatically improve single biometrics, achieving an Equal Error Rate 0.08% rate 100%.