Journal ArticleDOI
An approach for iris contact lens detection and classification using ensemble of customized DenseNet and SVM
Reads0
Chats0
TLDR
A novel Densely Connected Contact Lens Detection Network (DCLNet) has been proposed, which is a deep convolutional network with dense connections among layers, which improves the Correct Classification Rate (CCR) up to 4% as compared to the state of the arts.About:
This article is published in Future Generation Computer Systems.The article was published on 2019-12-01. It has received 38 citations till now. The article focuses on the topics: Contact lens & Iris recognition.read more
Citations
More filters
Journal ArticleDOI
An effective deep learning features based integrated framework for iris detection and recognition
TL;DR: An effective deep learning (DL) based integrated model for precise iris detection, segmentation and recognition that shows maximum recognition accuracy of 99.14% which is superior to other methods such as UniNet.
Journal ArticleDOI
Local binary hexagonal extrema pattern (LBHXEP): a new feature descriptor for fake iris detection
TL;DR: A novel and proficient feature descriptor, i.e., local binary hexagonal extrema pattern for fake iris detection is proposed, which exploits the relationship between the center pixel and its Hexa neighbor and solves the “curse of dimensionality” problem in liveness detection.
Journal ArticleDOI
Iris anti-spoofing through score-level fusion of handcrafted and data-driven features
TL;DR: A novel fusion-based approach to discriminate live iris from contact lens images that combines handcrafted and data-driven features and is performed using Nemenyi and Bonferroni-Dunn tests, where the proposed approach significantly improves the state of the arts.
Journal ArticleDOI
An approach for tool wear prediction using customized DenseNet and GRU integrated model based on multi-sensor feature fusion
Journal ArticleDOI
Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models
TL;DR: Three distinct models based on the ensemble of convolutional and residual blocks are proposed to enrich heterogeneous (cross-sensor) iris recognition and it is inferred that the proposed approach constitutes vital discerning iris features and can recognize that the micro-patterns exist inside the iris region.
References
More filters
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Book ChapterDOI
Large-Scale Machine Learning with Stochastic Gradient Descent
TL;DR: A more precise analysis uncovers qualitatively different tradeoffs for the case of small-scale and large-scale learning problems.
Journal ArticleDOI
High confidence visual recognition of persons by a test of statistical independence
TL;DR: A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence, which implies a theoretical "cross-over" error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates.
Journal ArticleDOI
How iris recognition works
TL;DR: Algorithms developed by the author for recognizing persons by their iris patterns have now been tested in many field and laboratory trials, producing no false matches in several million comparison tests.
Book ChapterDOI
Evaluation of pooling operations in convolutional architectures for object recognition
TL;DR: The aim is to gain insight into different functions by directly comparing them on a fixed architecture for several common object recognition tasks, and empirical results show that a maximum pooling operation significantly outperforms subsampling operations.