Exploring the feasibility of iris recognition for visible spectrum iris images obtained using smartphone camera

Trokielewicz, Mateusz; Bartuzi, Ewelina; Michowska, Katarzyna; Andrzejewska, Antonina; Selegrat, Monika

doi:10.1117/12.2205913

Cited by 12 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The training data for our study were sourced from a combination of publicly available iris image databases: CASIAv3 (2639 images from 395 classes) [21], a subset of ND-Iris-0405 (1283 images from 402 classes) [22], Warsaw-BioBase (1905 images from 135 classes) [23], BATH (148 images from 148 classes) [24], Biosec (1200 images from 150 classes) [25], and a proprietary dataset curated specifically for this research containing 2525 images captured in visible light, representing 97 distinct irises (only the red channel of the RGB color space was utilized). Figure 1 showcases representative data samples from each dataset.…”

Section: Training Iris Image Databasesmentioning

confidence: 99%

Synthetic Iris Images: A Comparative Analysis between Cartesian and Polar Representation

Kordas,

Bartuzi-Trokielewicz,

Ołowski

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

In recent years, the advancement of generative techniques, particularly generative adversarial networks (GANs), has opened new possibilities for generating synthetic biometric data from different modalities, including—among others—images of irises, fingerprints, or faces in different representations. This study presents the process of generating synthetic images of human irises, using the recent StyleGAN3 model. The novelty presented in this work consists in producing generated content in both Cartesian and polar coordinate representations, typically used in iris recognition pipelines, such as the foundational work proposed by John Daugman, but hitherto not used in generative AI experiments. The main objective of this study was to conduct a qualitative analysis of the synthetic samples and evaluate the iris texture density and suitability for meaningful feature extraction. During this study, a total of 1327 unique irises were generated, and experimental results carried out using the well-known OSIRIS open-source iris recognition software and the equivalent software, wordlcoin-openiris, newly published at the end of 2023 to prove that (1) no “identity leak” from the training set was observed, and (2) the generated irises had enough unique textural information to be successfully differentiated between both themselves and between them and real, authentic iris samples. The results of our research demonstrate the promising potential of synthetic iris data generation as a valuable tool for augmenting training datasets and improving the overall performance of iris recognition systems. By exploring the synthetic data in both Cartesian and polar representations, we aim to understand the benefits and limitations of each approach and their implications for biometric applications. The findings suggest that synthetic iris data can significantly contribute to the advancement of iris recognition technology, enhancing its accuracy and robustness in real-world scenarios by greatly augmenting the possibilities to gather large and diversified training datasets.

show abstract

Section: Training Iris Image Databasesmentioning

confidence: 99%

Synthetic Iris Images: A Comparative Analysis between Cartesian and Polar Representation

Kordas,

Bartuzi-Trokielewicz,

Ołowski

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Desta forma, as imagens geradas dentro desse espectro revelam informações relacionadas fundamentalmente à textura da íris ao invés da pigmentação da íris. Contudo, existem estudos que mostram o uso das câmeras comuns, como os dos dispositivos móveis [15], para a realização do reconhecimento, sendo que as imagens desta natureza possuem suas limitações, principalmente quando a cor da íris é escura. Existem diferentes modelos de equipamentos, os binoculares capazes de realizar a captura/leitura dos dois olhos (direito/esquerdo) ao mesmo tempo.…”

Section: Aquisição Da Imagemunclassified

Melhoria da Segurança de um Sistema de Informação Utilizando Biometria de Iris

França

Rodríguez

Rosa

2017

Anais Do Simpósio Brasileiro De Sistemas De Informação (SBSI)

View full text Add to dashboard Cite

RESUMOEste artigo descreve um sistema de segurança para ser utilizado em sistemas de informação baseado na biometria da íris. O processo de autenticação de usuários em um sistema de informação é de suma importância e pode ser realizado usando diversos métodos como: senhas alfanuméricas, certificação digital, dispositivos eletrônicos gerador de senhas ou sistemas que reconhecem características humanas, como é o caso da íris. Um sistema biométrico de íris consta das seguintes etapas: aquisição, segmentação, normalização, extração de padrões e finalmente a etapa de reconhecimento, que consiste na verificação ou validação do usuário no sistema. Cada uma dessas etapas possui relação com o desempenho do sistema biométrico. Nesse contexto, o objetivo principal deste trabalho é estudar o impacto da qualidade da imagem da íris, na etapa de aquisição e o seu desempenho global do sistema biométrico implementado, estabelecendo limiares mínimos de qualidade para garantir uma adequada autenticação do usuário no sistema. Os resultados experimentais demonstraram que os parâmetros de falsa aceitação e rejeição diminuem se um limiar de qualidade é estabelecido. ABSTRACTThis article describes a security system to be used in information systems based on iris biometrics. The process of authenticating users in an information system is relevant and can be accomplished using several methods such as alphanumeric passwords, digital certification, electronic devices, password generator or systems that recognize human characteristics such as the iris. A biometric iris system consists of the following steps: acquisition, segmentation, normalization, pattern extraction and finally the recognition step, which consists in the verification or validation of the user in the system. Each of these steps is related to the performance of the biometric system. In this context, the main objective of this work is to study the impact of the iris image quality in the acquisition stage and its overall performance of the implemented biometric system, establishing minimum quality thresholds to guarantee an adequate user authentication in the system. The experimental results demonstrated that the false acceptance and rejection parameters decrease if a threshold quality is established.

show abstract

“…Recently, these researchers also investigated a new setup for capturing iris images in white LED illumination using mobile devices [18], achieving recognition accuracy of up to 90% GMR (Genuine Match Rate) with 0.1% FMR (False Match Rate) using a combination of Daugman method and images captured with Nokia Lumia 1020 device. Our own previous experiments devoted to the field of visible light iris recognition were presented in [25]. We managed to achieve EERs not exceeding 8% for two commercial iris recognition methods with iris images collected using a smartphone camera.…”

Section: Related Workmentioning

confidence: 99%

Iris recognition with a database of iris images obtained in visible light using smartphone camera

Trokielewicz

2016

2016 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

Self Cite

View full text Add to dashboard Cite

This paper delivers a new database of iris images collected in visible light using a mobile phone's camera and presents results of experiments involving existing commercial and open-source iris recognition methods, namely: IriCore, VeriEye, MIRLIN and OSIRIS. Several important observations are made.First, we manage to show that after simple preprocessing, such images offer good visibility of iris texture even in heavily-pigmented irides. Second, for all four methods, the enrollment stage is not much affected by the fact that different type of data is used as input. This translates to zero or close-to-zero Failure To Enroll, i.e., cases when templates could not be extracted from the samples. Third, we achieved good matching accuracy, with correct genuine match rate exceeding 94.5% for all four methods, while simultaneously being able to maintain zero false match rate in every case. Correct genuine match rate of over 99.5% was achieved using one of the commercial methods, showing that such images can be used with the existing biometric solutions with minimum additional effort required. Finally, the experiments revealed that incorrect image segmentation is the most prevalent cause of recognition accuracy decrease.To our best knowledge, this is the first database of iris images captured using a mobile device, in which image quality exceeds this of a near-infrared illuminated iris images, as defined in ISO/IEC 19794-6 and 29794-6 documents. This database will be publicly available to all researchers.

show abstract

Exploring the feasibility of iris recognition for visible spectrum iris images obtained using smartphone camera

Cited by 12 publications

References 9 publications

Synthetic Iris Images: A Comparative Analysis between Cartesian and Polar Representation

Synthetic Iris Images: A Comparative Analysis between Cartesian and Polar Representation

Melhoria da Segurança de um Sistema de Informação Utilizando Biometria de Iris

Iris recognition with a database of iris images obtained in visible light using smartphone camera

Contact Info

Product

Resources

About