Unsupervised Domain Adaptation for Cross-sensor Pore Detection in High-resolution Fingerprint Images
This addresses the need for robust automated fingerprint recognition systems by improving pore detection across sensor types, though it is incremental as it builds on existing deep learning methods with a domain adaptation twist.
The paper tackles the problem of domain adaptability for pore detection in high-resolution fingerprint images across different sensors, proposing DeepDomainPore, which achieves state-of-the-art performance with an 88.12% true detection rate and 83.82% F-score in cross-sensor scenarios.
With the emergence of high-resolution fingerprint sensors, there has been a lot of focus on level-3 fingerprint features, especially the pores, for the next generation automated fingerprint recognition systems (AFRS). Following the success of deep learning in various computer vision tasks, researchers have developed learning-based approaches for detection of pores in high-resolution fingerprint images. Generally, learning-based approaches provide better performance than handcrafted feature-based approaches. However, domain adaptability of the existing learning-based pore detection methods has never been studied. In this paper, we study this aspect and propose an approach for pore detection in cross-sensor scenarios. For this purpose, we have generated an in-house 1000 dpi fingerprint dataset with ground truth pore coordinates (referred to as IITI-HRFP-GT), and evaluated the performance of the existing learning-based pore detection approaches. The core of the proposed approach for detection of pores in cross-sensor scenarios is DeepDomainPore, which is a residual learning-based convolutional neural network(CNN) trained for pore detection. The domain adaptability in DeepDomainPore is achieved by embedding a gradient reversal layer between the CNN and a domain classifier network. The proposed approach achieves state-of-the-art performance in a cross-sensor scenario involving public high-resolution fingerprint datasets with 88.12% true detection rate and 83.82% F-score.