使饥饿 发表于 2025-3-26 21:46:56

http://reply.papertrans.cn/27/2647/264602/264602_31.png

取消 发表于 2025-3-27 04:12:57

http://reply.papertrans.cn/27/2647/264602/264602_32.png

foodstuff 发表于 2025-3-27 08:39:27

Latent Fingerprint Image Segmentation Using Deep Neural Networkd on RBMs learns fingerprint image patches in two phases. The first phase (unsupervised pre-training) involves learning an identity mapping of the input image patches. In the second phase, fine-tuning and gradient updates are performed to minimize the cost function on the training dataset. The resul

NEXUS 发表于 2025-3-27 13:13:47

http://reply.papertrans.cn/27/2647/264602/264602_34.png

膝盖 发表于 2025-3-27 15:55:39

Iris Segmentation Using Fully Convolutional Encoder–Decoder Networksd networks, we apply a selection of conventional (non-CNN) iris segmentation algorithms on the same datasets, and similarly evaluate their performances. The results then get compared against those obtained from the FCEDNs. Based on the results, the proposed networks achieve superior performance over

Gudgeon 发表于 2025-3-27 20:02:54

http://reply.papertrans.cn/27/2647/264602/264602_36.png

规范就好 发表于 2025-3-28 00:51:27

http://reply.papertrans.cn/27/2647/264602/264602_37.png

overwrought 发表于 2025-3-28 04:48:49

http://reply.papertrans.cn/27/2647/264602/264602_38.png

有权 发表于 2025-3-28 08:53:10

http://reply.papertrans.cn/27/2647/264602/264602_39.png

inveigh 发表于 2025-3-28 11:15:50

Deep Triplet Embedding Representations for Liveness Detectionfingerprints are dissimilar from the ones generated artificially. A variant of the triplet objective function is employed, that considers patches taken from two real fingerprint and a replica (or two replicas and a real fingerprint), and gives a high penalty if the distance between the matching coup
页: 1 2 3 [4] 5
查看完整版本: Titlebook: Deep Learning for Biometrics; Bir Bhanu,Ajay Kumar Book 2017 Springer International Publishing AG, part of Springer Nature 2017 Deep Learn