Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks

Bezerra, Cides S.; Laroca, Rayson; Lucio, Diego Rafael; Severo, Evair; Oliveira, Lucas Ferrari de; Britto, Alceu S.; Menotti, David

doi:10.1109/sibgrapi.2018.00043

Cited by 26 publications

(25 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For completeness, there are several other applications with ocular images based on deep learning such as: spoofing detection [33], recognition of mislabelled left and right iris images [34], liveness detection [35], iris–periocular region location/detection [36, 37], sclera and iris segmentation [38, 39], gender classification [40] and sensor model identification [41].…”

Section: Related Workmentioning

confidence: 99%

Deep representations for cross‐spectral ocular biometrics

Zanlorensi¹,

Lucio²,

Britto

et al. 2020

IET biom.

Self Cite

View full text Add to dashboard Cite

One of the major challenges in ocular biometrics is the crossspectral scenario, i.e., how to match images acquired in different wavelengths (typically visible (VIS) against near-infrared (NIR)). This article designs and extensively evaluates cross-spectral ocular verification methods, for both the closed and open-world settings, using well known deep learning representations based on the iris and periocular regions. Using as inputs the bounding boxes of nonnormalized iris/periocular regions, we fine-tune Convolutional Neural Network (CNN) models (based either on VGG16 or ResNet-50 architectures), originally trained for face recognition. Based on the experiments carried out in two publicly available cross-spectral ocular databases, we report results for intra-spectral and cross-spectral scenarios, with the best performance being observed when fusing ResNet-50 deep representations from both the periocular and iris regions. When compared to the state-of-the-art, we observed that the proposed solution consistently reduces the Equal Error Rate (EER) values by 90% / 93% / 96% and 61% / 77% / 83% on the crossspectral scenario and in the PolyU Bi-spectral and Cross-eye-crossspectral datasets. Lastly, we evaluate the effect that the "deepness" factor of feature representations has in recognition effectiveness, and -based on a subjective analysis of the most problematic pairwise comparisons -we point out further directions for this field of research.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep representations for cross‐spectral ocular biometrics

Zanlorensi¹,

Lucio²,

Britto

et al. 2020

IET biom.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Fully Convolutional Neural Networks (FCNN) are the natural evolution of the CNN for segmentation tasks [27], [28]. This kind of neural network delivers an image of equal size as the input image containing the segmented classes.…”

Section: B Semantic Segmentationmentioning

confidence: 99%

“…To reach that goal, this adds an upsampling layer. Bezerra et al [28] perform iris segmentation used the following databases: Casia v4, IITD, CrEye-Iris.…”

Section: B Semantic Segmentationmentioning

confidence: 99%

Semantic Segmentation of Periocular Near-Infra-Red Eye Images Under Alcohol Effects

et al. 2021

View full text Add to dashboard Cite

This paper proposes a new framework to detect, segment, and estimate the localization of the eyes from a periocular Near-Infra-Red iris image under alcohol consumption. This stage will take part in the final solution to measure the fitness for duty. Fitness systems allow us to determine whether a person is physically or psychologically able to perform their tasks. Our segmentation framework is based on an object detector trained from scratch to detect both eyes from a single image. Then, two efficient networks were used for semantic segmentation; a Criss-Cross attention network and DenseNet10, with only 122,514 and 210,732 parameters, respectively. These networks can find the pupil, iris, and sclera. In the end, the binary output eye mask is used for pupil and iris diameter estimation with high precision. Five state-of-theart algorithms were used for this purpose. A mixed proposal reached the best results. A second contribution is establishing an alcohol behavior curve to detect the alcohol presence utilizing a stream of images captured from an iris instance. Also, a manually labeled database with more than 20k images was created. Our best method obtains a mean Intersection-over-Union of 94.54% with DenseNet10 with only 210,732 parameters and an error of only 1-pixel on average.INDEX TERMS Biometrics, Fitness for duty, segmentation, iris, alcohol.

show abstract

“…As stated by Cordts et al [25], coarse annotations are intended to support research areas that exploit large volumes of data. We also automatically generated 38,851 bounding boxes using the iris segmentation approach proposed by Bezerra et al [26] for 3 well-known near-infrared (NIR) spectral databases. We manually checked and corrected (if necessary) all annotations.…”

Section: Introductionmentioning

confidence: 99%

“…We chose the approach proposed in [26] due to the fact that it presented an error rate lower than 1.5% in the aforementioned NIR databases. However, despite the good results presented by that segmentation approach, the detection task is much less expensive in terms of both computational cost and data annotation.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous Iris and Periocular Region Detection Using Coarse Annotations

Lucio

Laroca

Zanlorensi

et al. 2019

2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

Self Cite

View full text Add to dashboard Cite

In this work, we propose to detect the iris and periocular regions simultaneously using coarse annotations and two well-known object detectors: YOLOv2 and Faster R-CNN. We believe coarse annotations can be used in recognition systems based on the iris and periocular regions, given the much smaller engineering effort required to manually annotate the training images. We manually made coarse annotations of the iris and periocular regions (≈ 122K images from the visible (VIS) spectrum and ≈ 38K images from the near-infrared (NIR) spectrum). The iris annotations in the NIR databases were generated semi-automatically by first applying an iris segmentation CNN and then performing a manual inspection. These annotations were made for 11 well-known public databases (3 NIR and 8 VIS) designed for the iris-based recognition problem, and are publicly available to the research community 1 . Experimenting our proposal on these databases, we highlight two results. First, the Faster R-CNN + Feature Pyramid Network (FPN) model reported an Intersection over Union (IoU) higher than YOLOv2 (91.86% vs 85.30%). Second, the detection of the iris and periocular regions being performed simultaneously is as accurate as performed separately, but with a lower computational cost, i.e., two tasks were carried out at the cost of one.

show abstract

Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks

Cited by 26 publications

References 40 publications

Deep representations for cross‐spectral ocular biometrics

Deep representations for cross‐spectral ocular biometrics

Semantic Segmentation of Periocular Near-Infra-Red Eye Images Under Alcohol Effects

Simultaneous Iris and Periocular Region Detection Using Coarse Annotations

Contact Info

Product

Resources

About