Fingerprints　recognition　(FPR)　is　considered　as　a　secure　and　efficient　way　of　personal　identification　verification.　However,　research　of　fake　fingerprints　generation　by　generative　adversarial　networks　(GAN)　disclosed　a　potential　vulnerability　of　partial　FPR　systems.　In　this　paper,　we　proposed　two　networks　based　on　deep　convolutional　generative　adversarial　networks　(DCGAN)　to　improve　the　performance　of　DCGAN　by　enhancing　the　performance　of　the　discriminator.　More　specifically,　the　structure　of　discriminators　in　our　network　is　modified　by　two　approximate　typical　convolutional　neural　networks,　AlexNet　and　VGG11.　(We　abbreviated　them　to　Alex-GAN　and　VGG-GAN　respectively)　We　evaluated　the　output　of　generators　in　our　models　by　cosine　similarity　index　every　10　epochs　during　training,　which　monitored　the　performance　of　the　generator　and　was　convenient　for　comparing　two　models.　The　results　of　cosine　similarity　and　texture　analysis　show　that　VGG-GAN　performs　better　than　Alex-GAN.　Although　our　models　are　unstable　and　unbalanced　in　discriminator　and　generator,　we　acquired　notable　results　unexpectedly　which　demonstrate　the　competitiveness　of　our　model.　©　2021　IEEE.