Learning modality-invariant binary descriptor for crossing palmprint to palm-vein recognition

Palmprint has shown promising potential for biometrics recognition due to its excellent contactless and hygienic properties. However, most existing methods focus only on feature learning of unimodal palmprint images leading to the challenge of palmprint recognition crossing different modalities. In this paper, we propose a modality-invariant binary features learning (MIBFL) method for crossing palmprint to palm-vein recognition, where palm images are captured under visible and invisible near-infrared illumination, respectively. We first map the multiple modal palm images into their high-dimensional alignment representation to reduce the impact of misalignment and noise between different image modalities. Then, we simultaneously learn the discriminative features from different modalities of alignment images via matrix factorization by enforcing the orthogonal and balanced constraints. Lastly, we jointly learn a pair of encoding functions to project multi-modal palm features into the common binary feature descriptor for crossing palmprint to palm-vein recognition. Experimental results on the widely used PolyU multi-spectral palmprint database are presented to demonstrate the effectiveness of the proposed MIBFL method.