A Direct Fingerprint Minutiae Extraction Approach Based on Convolutional Neural Networks

Minutiae, as the essential features of fingerprints, play a significant role in fingerprint recognition systems. Most existing minutiae extraction methods are based on a series of hand-defined preprocesses such as binarization, thinning and enhancement. However, these preprocesses require strong prior knowledge and are always lossy operations. And that will lead to dropped or false extractions of minutiae. In this paper, a novel minutiae extraction approach based on deep convolutional neural networks is proposed, which directly extract minutiae on raw fingerprint images without any preprocess since we tactfully take the advantage of the strong representative capacity of deep convolutional neural networks. Minutiae can be effectively extracted due to the well designed architectures. Furthermore, the accuracy is guaranteed in that the comprehensive estimate is made to eliminate spurious minutiae. Moreover, a number of implement skills are employed both to avoid overfitting and to improve the robustness. This approach makes a good performance because it not only makes all use of information in fingerprint images but also learns the minutiae patterns from large amounts of data. Comparisons are made with previous works and a widely applied commercial fingerprint identification system. Results show that our approach performs better both in accuracy and robustness.