Broad Learning with Uniform Local Binary Pattern for Fingerprint Liveness Detection

Abstract

AbstractRecently, with the widespread application of mobile communication devices, fingerprint identification is the most prevalent in all types of mobile computing. While they bring a huge convenience to our lives, the resulting security and privacy issues have caused widespread concern. Fraudulent attack using forged fingerprint is one of the typical attacks to realize illegal intrusion. Thus, fingerprint liveness detection (FLD) for True or Fake fingerprints is very essential. This paper proposes a novel fingerprint liveness detection method based on broad learning with uniform local binary pattern (ULBP). Compared to convolutional neural networks (CNN), training time is drastically reduced. Firstly, the region of interest of the fingerprint image is extracted to remove redundant information. Secondly, texture features in fingerprint images are extracted via ULBP descriptors as the input to the broad learning system (BLS). ULBP reduces the variety of binary patterns of fingerprint features without losing any key information. Finally, the extracted features are fed into the BLS for training. The BLS is a flat network, which transfers and places the original input as a mapped feature in feature nodes, generalizing the structure in augmentation nodes. Experiments show that in Livdet 2011 and Livdet 2013 datasets, the average training time is about 1 s and the performance of identifying real and fake fingerprints is effect. Compared to other advanced models, our method is faster and more miniature.KeywordsFingerprint liveness detectionBroad learningULBPBiometricsReal-time