Ocular recognition databases and competitions: a survey

Zanlorensi, Luiz A.; Laroca, Rayson; Luz, Eduardo; Britto, Alceu S.; Oliveira, Luiz S.; Menotti, David

doi:10.1007/s10462-021-10028-w

Cited by 10 publications

(14 citation statements)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, several ocular contests and datasets have been released to evaluate state-of-the-art methods for many applications. Zanlorensi et al 7 detailed and described several datasets and contests for iris and periocular recognition. Different problems have been addressed by the researchers, such as ocular recognition in unconstrained environments, ocular recognition on cross-spectral scenarios, iris/periocular region detection, iris/periocular region segmentation, and sclera segmentation 44 .…”

Section: Related Workmentioning

confidence: 99%

“…As described in 7 , datasets containing images obtained at the Near-infraRed (NIR) wavelength were created mainly to investigate the intricate patterns present in the iris region 45 , 46 . There are also other studies on NIR ocular images, such as generating synthetic iris images 47 , 48 , spoofing and liveness detection 49 – 52 , contact lens detection 53 – 56 , and template aging 57 , 58 .…”

Section: Related Workmentioning

confidence: 99%

“…Biometric systems that use ocular images have been extensively investigated due to the high level of singularity in the iris and because the periocular region can provide discriminative patterns even in noisy images 1 – 6 . The term ocular comprises the periocular and iris regions 7 . The periocular region comprises eyebrows, eyelashes and eyelids, while the iris is the colored region between the sclera and pupil.…”

Section: Introductionmentioning

confidence: 99%

“…The results achieved by the proposed methods have shown that it is challenging to develop a robust biometric system in such conditions, mainly due to the high intra-class variability. Based on recent works 2 , 5 , 7 , we can state that developing an ocular biometric system that operates in unconstrained environments is still a challenging task, especially with images obtained by mobile devices. In this condition, the images captured by the volunteer may present several variations caused by occlusion, pose, eye gaze, off-angle, distance, resolution, and image quality (affected by the mobile device).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A new periocular dataset collected by mobile devices in unconstrained scenarios

Zanlorensi

Laroca

Lucio

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Recently, ocular biometrics in unconstrained environments using images obtained at visible wavelength have gained the researchers’ attention, especially with images captured by mobile devices. Periocular recognition has been demonstrated to be an alternative when the iris trait is not available due to occlusions or low image resolution. However, the periocular trait does not have the high uniqueness presented in the iris trait. Thus, the use of datasets containing many subjects is essential to assess biometric systems’ capacity to extract discriminating information from the periocular region. Also, to address the within-class variability caused by lighting and attributes in the periocular region, it is of paramount importance to use datasets with images of the same subject captured in distinct sessions. As the datasets available in the literature do not present all these factors, in this work, we present a new periocular dataset containing samples from 1122 subjects, acquired in 3 sessions by 196 different mobile devices. The images were captured under unconstrained environments with just a single instruction to the participants: to place their eyes on a region of interest. We also performed an extensive benchmark with several Convolutional Neural Network (CNN) architectures and models that have been employed in state-of-the-art approaches based on Multi-class Classification, Multi-task Learning, Pairwise Filters Network, and Siamese Network. The results achieved in the closed- and open-world protocol, considering the identification and verification tasks, show that this area still needs research and development.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A new periocular dataset collected by mobile devices in unconstrained scenarios

Zanlorensi

Laroca

Lucio

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Additionally, the annotation of such large-scale datasets is today (in most cases) still a manual, labor-intensive, and time-consuming task. These points are especially true for datasets dedicated to the segmentation of ocular images (in various imaging domains), where, next to the data collection, the generation of high-quality (multi-class) semantic annotations is known to be a costly endeavor [40,42].…”

Section: Introductionmentioning

confidence: 99%

BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images

Tomašević¹,

Peer²

2022

Preprint

View full text Add to dashboard Cite

Current state-of-the-art segmentation techniques for ocular images are critically dependent on large-scale annotated datasets, which are labor-intensive to gather and often raise privacy concerns. In this paper, we present a novel framework, called BiOcularGAN, capable of generating synthetic large-scale datasets of photorealistic (visible light and near infrared) ocular images, together with corresponding segmentation labels to address these issues. At its core, the framework relies on a novel Dual-Branch StyleGAN2 (DB-StyleGAN2) model that facilitates bimodal image generation, and a Semantic Mask Generator (SMG) that produces semantic annotations by exploiting DB-StyleGAN2's feature space. We evaluate BiOcu-larGAN through extensive experiments across five diverse ocular datasets and analyze the effects of bimodal data generation on image quality and the produced annotations. Our experimental results show that BiOcularGAN is able to produce high-quality matching bimodal images and annotations (with minimal manual intervention) that can be used to train highly competitive (deep) segmentation models that perform well across multiple real-world datasets. The source code will be made publicly available.

show abstract

Periocular biometrics and its relevance to partially masked faces: A survey

Sharma

Ross²

2023

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Ocular recognition databases and competitions: a survey

Cited by 10 publications

References 154 publications

A new periocular dataset collected by mobile devices in unconstrained scenarios

A new periocular dataset collected by mobile devices in unconstrained scenarios

BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images

Periocular biometrics and its relevance to partially masked faces: A survey

Contact Info

Product

Resources

About