Ridgeformer: Mutli-Stage Contrastive Training For Fine-grained Cross-Domain Fingerprint Recognition

Abstract

The increasing demand for hygienic and portable biometric systems has underscored the need for advances in contactless fingerprint recognition. Contactless acquisition introduces challenges such as focus variation, reduced ridge-valley contrast, finger-position variation, and perspective distortion. Ridgeformer is a multi-stage transformer-based approach that captures global spatial features and refines localized feature alignment across fingerprint samples for fine-grained cross-domain contactless fingerprint recognition.

Publication
IEEE International Conference on Image Processing (ICIP), 2025