Deep Feature Collaboration for Challenging 3D Finger Knuckle Identification

Contactless 3D finger knuckle pattern is a new biometric identifier which offers highly discriminative features for the finger knuckle based personal identification. State-of-the-art methods for object recognition, a more generic problem, employ deep neural network based approaches and demonstrate superior effectiveness. However, any direct applications from those methods do not outperform specialized hand-crafted feature description approaches for the problem addressed in this paper. In addition, such deep neural network based methods have to address challenges associated with emerging biometrics, e.g. availability of very limited training data, large intra-class or train-test sample variations as observed for the real applications, etc. This paper attempts to address the above challenges and introduces a new deep neural network based approach for the contactless 3D finger knuckle identification. Our approach simultaneously encodes and incorporates deep features from multiple scales to form a more robust deep feature representation. Such collaborative feature representations are robustly matched using an efficient alignment scheme with a fully convolutional architecture to accommodate involuntary finger variations during the contactless imaging. Comparative experimental results in the two-session 3D finger knuckle images database, acquired from over 200 subjects and is publicly introduced from this paper, illustrate superior performance over the state-of-the-art methods, e.g. offering ~22% GAR improvement at extremely low FAR under challenging comparison scenarios. Additional experiments in other publicly available databases including 3D palmprint, 3D fingerprint, and 2D finger knuckle further validate the effectiveness and demonstrate the generalizability of the proposed approach.