This paper presents a Dempster Shafer theory based classi-fier fusion algorithm to improve the performance of fingerprint verifica-tion. The proposed fusion algorithm combines decision induced match scores of minutiae, ridge, fingercode and pore based fingerprint verifica-tion algorithms and provides an improvement of at least 8.1% in the ver-ification accuracy compared to the individual algorithms. Further, pro-posed fusion algorithm outperforms by at least 2.52% when compared with existing fusion algorithms. We also found that the use of Demp-ster's rule of conditioning reduces the training time by approximately 191 seconds.