End-to-End Fingerprints Liveness Detection using Convolutional Networks with Gram module

التفاصيل البيبلوغرافية
العنوان: End-to-End Fingerprints Liveness Detection using Convolutional Networks with Gram module
المؤلفون: Park, Eunsoo, Cui, Xuenan, Kim, Weonjin, Kim, Hakil
سنة النشر: 2018
المجموعة: Computer Science
مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition
الوصف: This paper proposes an end-to-end CNN(Convolutional Neural Networks) model that uses gram modules with parameters that are approximately 1.2MB in size to detect fake fingerprints. The proposed method assumes that texture is the most appropriate characteristic in fake fingerprint detection, and implements the gram module to extract textures from the CNN. The proposed CNN structure uses the fire module as the base model and uses the gram module for texture extraction. Tensors that passed the fire module will be joined with gram modules to create a gram matrix with the same spatial size. After 3 gram matrices extracted from different layers are combined with the channel axis, it becomes the basis for categorizing fake fingerprints. The experiment results had an average detection error of 2.61% from the LivDet 2011, 2013, 2015 data, proving that an end-to-end CNN structure with few parameters that is able to be used in fake fingerprint detection can be designed.
Comment: 15 pages, 7 figures
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/1803.07830
رقم الأكسشن: edsarx.1803.07830
قاعدة البيانات: arXiv