Convolutional neural networks (CNNs) were popular in ImageNet large scale visual recognition competition (ILSVRC 2012) because of their identification ability and computational efficiency. This paper proposes a palm vein recognition method based on CNN. The four main steps of palm vein recognition are image acquisition, image preprocessing, feature extraction, and matching. To reduce the processing steps in the recognition of palm vein images, a palm vein recognition method using a CNN is proposed. CNN is a deep learning network. Palm vein images are acquired using near-infrared light, under which the veins in the palm of the hand are relatively prominent. To obtain a good vein image, many previous methods used preprocessing to further enhance the image before using feature extraction to find feature matches for further comparison. In recent years, CNNs have been shown to have great advantages and have performed well in image classification. To reduce early-stage image processing, a CNN is used to classify and recognize palm vein images. The networks AlexNet and VGG depth CNN were trained to extract image features. The palm vein recognition rates by VGG-19, VGG-16, and AlexNet were 98.5%, 97.5%, and 96%, respectively.
Pub. online:1 Jan 2017Type:Research ArticleOpen Access
Volume 28, Issue 3 (2017), pp. 471–484
ID-based cryptographic protocol is an extremely valuable apparatus in the field of cryptography and has numerous latent applications. The safety of conventional ID-based cryptographic protocol is entirely contingent in light of the safety of private keys. Revelation of private keys needs reissuing all beforehand doled out encryptions. This confinement turns out to be clearer today as key presentation is more regular with expanding utilization of unprotected gadgets and mobile technology. In this context, relieving the loss of key disclosure in ID-based cryptographic protocol is a critical issue. To manage this issue, we present to include onward security into ID-based cryptographic protocol. Besides, we propose another development of indistinguishability-ID-based cryptographic protocol using Integer Factorization Problem (IFP) and Generalized Discrete Logarithm Problem (GDLP) which is semantically protected against Chosen Plaintext Attack (CPA) in random oracle. We show that our presented protocol beats the other standing protocol as far as security, the length of public key and computational cost are concerned. We shed light on some applications and future scope.
Pub. online:1 Jan 2001Type:Research ArticleOpen Access
Volume 12, Issue 2 (2001), pp. 297–302
Yamaguchi, Okayama, and Miyahara proposed a simple but efficient authentication system, SPLICE/AS. In this article, we show that their method is vulnerable to the guessing attack. An attacker can obtain the password, private-key, and public-key of the user. To overcome the vulnerability of SPLICE/AS to the guessing attack, we propose an improvement of their system. In our scheme, we not only prevent the guessing attack to obtain secret messages but also enhance the security of the SPLICE/AS authentication system in WIDE.