Fingerprint classification with a new deep neural network model: robustness for different captures of the same fingerprints

The growth of fingerprint databases creates a need for strategies to reduce the identification time. Fingerprint classification reduces the search penetration rate by grouping the fingerprints into several classes. Typically, features describing the visual patterns of a fingerprint are extracted and fed to a classifier. The extraction can be time-consuming and error-prone, especially for fingerprints whose visual classification is dubious, and often includes a criterion to reject ambiguous fingerprints. In this paper, we propose to improve on this manually designed process by using deep neural networks, which extract implicit features directly from the images and perform the classification within a single learning process. We give a particular focus to the robustness of the classification, which we define as the consistent assignation of the same class to different captures of the same fingerprint, allowing for a maximum reduction of the penetration rate. With this objective in mind, we propose a specific network to tackle the classification problem. An extensive experimental study assesses that convolutional neural networks outperform all other tested approaches in terms of both accuracy and robustness, while not incurring into the rejection of low quality input fingerprints. The runtime of convolutional networks is also lower than that of combining feature extraction procedures with classification algorithms.