Robust Partial Fingerprint Recognition.

Low quality capture and obstruction on fingers often result in partially visible fingerprint images, which imposes challenge for fingerprint recognition. In this work, motivated from the practical use cases, we first systematically studied different types of partial occlusion. Specifically, two major types of partial occlusion, including six granular types, and the corresponding methods to simulate each type for model evaluation and improvement were introduced. Second, we proposed a novel Robust Partial Fingerprint (RPF) recognition framework to mitigate the performance degradation due to occlusion. RPF effectively encodes the knowledge about partial fingerprints through occlusion-enhanced data augmentation, and explicitly captures the missing regions for robust feature extraction through occlusion-aware modeling. Finally, we demonstrated the effectiveness of RPF through extensive experiments. Particularly, baseline fingerprint recognition models can degrade the recognition accuracy measured in FRR @ FAR=0.1% from 14.67% to 17.57% at 10% occlusion ratio on the challenging NIST dataset, while RPF instead improves the recognition performance to 9.99% under the same occlusion ratio. Meanwhile, we presented a set of empirical analysis through visual explanation, matching score analysis, and uncertainty modeling, providing insights into the recognition model’s behavior and potential directions of enhancement.