Automated identification of thoracolumbar vertebrae using orthogonal matching pursuit
Machine Vision and Applications
Hi-index | 0.00 |
We propose a novel Dynamic Programming Matching Pursuit (DPMP) algorithm for iris recognition. The method modifies the matching pursuit (MP) algorithm to select the most representative atoms for the iris recognition. In the experiments, we demonstrate that our system has (1) better performance for both personal identification and verification, and (2) a better ROC curve, (3) less computation than the conventional MP-based iris recognition.