دانلود رایگان مقاله ادغام چاپ بندانگشت با چاپ کف دست و رگهای پشت دست

ABSTRACT

To ensure the high performance of a biometric system, various unimodal systems are combined to evade their constraints to form a multimodal biometric system. Here, a multimodal personal authentication system using palmprint, dorsal hand vein pattern and a novel biometric modality “palm-phalanges print” is presented. Firstly, we have collected a new anterior hand database of 50 individuals with 500 images at the institute referred to as NSIT Palmprint Database 1.0 by using NSIT palmprint device. Then from these anterior hand images, database for palmprint and palm-phalanges is created. In this biometric system, the individuals do not have to undergo the distress of using two different sensors since the palmprint and palm-phalanges print features can be captured from the same image, using NSIT palmprint device, at the same time. For dorsal hand vein, Bosphorus Hand Vein Database is used because of the stability and uniqueness of hand vein patterns. We propose fusion of three different biometric modalities which includes palmprint (PP), palm-phalanges print (PPP) and dorsal hand vein (DHV) and perform score level fusion of PP-PPP, PP-DHV, PPP-DHV and PP-PPP-DHV strategies. Lastly, we use K-nearest neighbor, support vector machine and random forest to validate the matching stage. The results proved the validity of our proposed modality and show that multimodal fusion has an edge over unimodal fusion.

10. Conclusion

In this paper, a new anterior hand database is created which is referred as NSIT Palmprint Database 1.0 by using a NSIT palmprint device. Along with this, a novel biometric modality “palm-phalanges print” has been proposed. Result shows that this modality can be used in recognition systems effectively. To further improve the performance of unimodal biometric system, fusion of palm-phalanges print with palmprint and dorsal hand vein is presented. In multimodal biometric system, complementary information is fused to overcome the drawbacks of the unimodal biometric systems. The results shown prove that the performance of multimodal biometric system is significantly improved as compared to the unimodal biometric systems. The fusion of palmprint and palm-phalanges print proved to be very efficient and effective to the users as well as to the recognition system because data for both the modalities is captured using same image before analysis is done. The score level fusion is attempted with PP-PPP, PP-DHV, PPP-DHV and PP-PPP-DHV strategies. Various conventional operators, Yager’s ordered weighted averaging (OWA) operator and t-norm fusion operators are used for score level fusion. On comparing the fusion rules, the convergence rate of ROC of frank T-norm fusion is better than other fusion rules thus outperforming others. While Hamacher T-norm, Yager’s OWA and Dubois–Prade shows the similar performance. Also the score level fusion of PP-PPPDHV performs better than other three. This shows that multimodal fusion is better than unimodal fusion.