Cross-Spectral Iris Matching Using Conditional Coupled GAN

Mostofa, Moktari; Taherkhani, Fariborz; Dawson, Jeremy; Nasrabadi, Nasser M.

doi:10.1109/ijcb48548.2020.9304929

Cited by 5 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2, respectively. Since most of the available iris galleries are acquired under NIR illumination and the opportunistic iris images are obtained under the VIS domain at higher resolution, in our first technique we find a mapping between the NIR and VIS During training, the contrastive loss function is used in the latent embedding subspace to optimize the network parameters so that latent features of iris images from different spectral domain of the same identity are close to each other while the features of different identities are pushed further apart [17].…”

Section: Methodsmentioning

confidence: 99%

“…The key reason behind developing this architecture is to learn the semantic similarity between two samples of the same subject but in different spectral domains. Therefore, inspired by our previous cpGAN architecture [17], we trained this network using a similarity measure based on a contrastive loss [52] to ensure that the distance between the images corresponding to the genuine pairs (VIS iris image and NIR iris image of the same person) is minimized, and that of the imposter pairs (VIS iris image and NIR iris image of the different persons) is maximized.…”

Section: Methodsmentioning

confidence: 99%

“…These underlying reasons motivated us to develop such a dedicated cross-spectral iris matcher, which is highly desirable. Hence, we have proposed a deep coupled learning framework for cross-spectral iris recognition, which utilizes a conditional coupled generative adversarial network (cpGAN) [17] to learn a common embedded feature vector via exploring the correlation between the NIR and VIS iris images in a reduced dimensional latent embedding feature subspace. The key benefits from our second iris recognition approach can be summarized as the following:…”

Section: Introductionmentioning

confidence: 99%

“…Architecture of our proposed conditional cpGAN framework. During training, the contrastive loss function is used in the latent embedding subspace to optimize the network parameters so that latent features of iris images from different spectral domain of the same identity are close to each other while the features of different identities are pushed further apart[17].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition

Mostofa

Dawson

Nasrabadi

2021

IEEE Trans. Biom. Behav. Identity Sci.

Self Cite

View full text Add to dashboard Cite

In recent years, cross-spectral iris recognition has emerged as a promising biometric approach to establish the identity of individuals. However, matching iris images acquired at different spectral bands (i.e., matching a visible (VIS) iris probe to a gallery of near-infrared (NIR) iris images or vice versa) shows a significant performance degradation when compared to intraband NIR matching. Hence, in this paper, we have investigated a range of deep convolutional generative adversarial network (DCGAN) architectures to further improve the accuracy of cross-spectral iris recognition methods. Moreover, unlike the existing works in the literature, we introduce a resolution difference into the classical cross-spectral matching problem domain. We have developed two different novel techniques using the conditional generative adversarial network (cGAN) as a backbone architecture for cross-spectral iris matching. In the first approach, we simultaneously address the cross-resolution and cross-spectral matching problem by training a cGAN that jointly translates cross-resolution as well as cross-spectral tasks to the same resolution and within the same spectrum. In the second approach, we design a coupled generative adversarial network (cpGAN) architecture consisting of a pair of cGAN modules that project the VIS and NIR iris images into a low-dimensional embedding domain to ensure maximum pairwise similarity between the feature vectors from the two iris modalities of the same subject. To assure the efficacy of our methods, we perform several experiments considering multiple real-life scenarios on three publicly-available cross-spectral iris datasets. Our best experimental results obtained from the cpGAN network outperform the existing benchmark convolutional neural network (CNN) with a supervised discrete hashing (SDH) approach [1] by as much as 1.67%, and 2.22% GAR at FAR of 0.01, while our cGAN provides recognition accuracy with significantly lower EER value of 1.5%, and 1.54% for PolyU bi-spectral dataset, and Cross-eyed-cross-spectral iris recognition database, respectively. It indicates the superiority of our approaches over results previously published in the literature.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition

Mostofa

Dawson

Nasrabadi

2021

IEEE Trans. Biom. Behav. Identity Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Instead of using NIR images alone, [38] uses both NIR and VIS iris images for matching. Their pre-processed images are fed into two separate generators, using discriminators that discriminate the spectral domain and contrast loss to optimize the generator parameters so that the generators can align different spectral iris image features from the same identity.…”

Section: Deep Learning Featuresmentioning

confidence: 99%

Deep Learning for Iris Recognition: A Review

Yin¹,

He²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Iris recognition is a secure biometric technology known for its stability and privacy. With no two irises being identical and little change throughout a person's lifetime, iris recognition is considered more reliable and less susceptible to external factors than other biometric recognition methods. Unlike traditional machine learning-based iris recognition methods, deep learning technology does not rely on feature engineering and boasts excellent performance. This paper collects 120 relevant papers to summarize the development of iris recognition based on deep learning. We first introduce the background of iris recognition and the motivation and contribution of this survey. Then, we present the common datasets widely used in iris recognition. After that, we summarize the key tasks involved in the process of iris recognition based on deep learning technology, including identification, segmentation, presentation attack detection, and localization. Finally, we discuss the challenges and potential development of iris recognition. This review provides a comprehensive sight of the research of iris recognition based on deep learning.

show abstract

A Survey on Iris Recognition Systems in Cross-Spectral Domain

Al-Kardhi,

Al-Juboori

2023

2023 International Conference on Information Technology, Applied Mathematics and Statistics (ICITAMS)

View full text Add to dashboard Cite

Cross-Spectral Iris Matching Using Conditional Coupled GAN

Cited by 5 publications

References 19 publications

Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition

Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition

Deep Learning for Iris Recognition: A Review

A Survey on Iris Recognition Systems in Cross-Spectral Domain

Contact Info

Product

Resources

About