Systems, Man, and Cybernetics

 

Home

• [P665] A Novel Method of Score Level Fusion Using Multiple Impressions for Fingerprint Verification
  Author(s): Ren Chunxiao, Yilong Yin, Jun Ma, Gongping Yang
  
  

  Abstract
  In this paper, we present a novel method of score level fusion using multiple enrolled impressions to achieve higher verification accuracy of existing uni-matcher fingerprint systems. The method we proposed constructs a wrapper method by utilizing one-on-one matching time after time within multiple enrolled impressions. At first, the multiple enrolled impressions are conversed to points in a multidimensional space via analyzing one-on-one matching results. Then the final matching result is achieved by calculating distance between query image and multiple enrolled impressions in the multidimensional space. The novel method of score level fusion outperforms the uni-matcher based scheme over a wide range of FAR and FRR values. The equal error rate of our method is observed to be 3.28%, while that of the uni-matcher is 8.02%.

  
   

Full Text (PDF)