Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition

Wang, Caiyong; Muhammad, Jawad; Wang, Yunlong; He, Zhaofeng; Sun, Zhenan

doi:10.1109/tifs.2020.2980791

Cited by 134 publications

(87 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In these methods, the inner and outer boundaries of the iris are initially identified, and then filtered iris masks are acquired through detecting the lower and upper eyelids and limbic regions. This means that iris localization is performed first, and then the iris segmentation process is performed [ 1 , 2 , 3 ]. The two traditional and most popular algorithms for iris segmentation were introduced by Professor Daugman’s integrodifferential operator [ 11 ] and Wilde’s circular Hough transforms [ 12 ].…”

Section: Related Workmentioning

confidence: 99%

“…Recent developments in the field of computer vision have led to renewed interest in biometrics technologies. Iris recognition has been determined as the most accurate and reliable biometric identification approach and thus it has been deployed in several applications such as identification and authentication systems, intelligent key systems, digital forensics, and border control [ 1 , 2 , 3 , 4 ]. An iris comprises a large amount of distinctive, constant, and forgery-proof features such as complex textures and explicit structural information for biometric identification [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

“…Comparatively, the iris-based system is foolproof and quite convenient to implement although it may require an infrared sensor and specially designed optics [ 1 , 9 ]. However, iris segmentation tasks are challenging because the acquisition of iris images may suffer from non-cooperative environments including specular reflection, off-angle iris, occlusion due to eyelash/eyelid/glasses, partially captured iris, etc., as shown in Figure 1 [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

“…A common iris recognition system often consists of the following procedures: Iris image acquisition, iris image pre-processing, iris segmentation, iris feature extraction, and feature matching for identification or authentication [ 1 , 3 , 4 , 6 , 10 ]. In the iris recognition system, iris segmentation is a critical and challenging task because of the unpredictable and irregular shape of the iris [ 4 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

Putri

Aslam

et al. 2021

Sensors

View full text Add to dashboard Cite

Iris segmentation plays an important and significant role in the iris recognition system. The prerequisite for accurate iris recognition is the correctness of iris segmentation. However, the efficiency and robustness of traditional iris segmentation methods are severely challenged in a non-cooperative environment because of unfavorable factors, for instance, occlusion, blur, low resolution, off-axis, motion, and specular reflections. All of the above factors seriously reduce the accuracy of iris segmentation. In this paper, we present a novel iris segmentation algorithm that localizes the outer and inner boundaries of the iris image. We propose a neural network model called “Interleaved Residual U-Net” (IRUNet) for semantic segmentation and iris mask synthesis. The K-means clustering is applied to select saliency points set in order to recover the outer boundary of the iris, whereas the inner border is recovered by selecting another set of saliency points on the inner side of the mask. Experimental results demonstrate that the proposed iris segmentation algorithm can achieve the mean IOU value of 98.9% and 97.7% for inner and outer boundary estimation, respectively, which outperforms the existing approaches on the challenging CASIA-Iris-Thousand database.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

Putri

Aslam

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Biometrics authentication technologies as a solution have been widely investigated in past years. Currently, various biometrics traits such as fingerprints [1], faces [2], irises [3], and veins [4] have been applied for personal authentication and can been broadly categorized two categories [5]: (1) extrinsic traits such as face, fingerprint, iris, and gait; (2) intrinsic traits such as finger-vein, palm vein, and hand vein. Extrinsic traits are vulnerable to copy and fake, which results some concerns on privacy and security in practice.…”

Section: Introductionmentioning

confidence: 99%

Finger-Vein Pattern Restoration With Generative Adversarial Network

et al. 2020

View full text Add to dashboard Cite

Finger-vein recognition technology has attracted more and more attention because of its high security and convenience. However, the finger-vein image capturing is affected by various factors, which results that some vein patterns are missed in acquired image. Matching minutiae features in such images ultimately degrades verification performance of the finger-vein recognition system. To overcome this problem, in this paper, a novel finger-vein image restoration approach is proposed to recover the missed patterns based on generative adversarial network (GAN), as the first attempt in this area. Firstly, we employ the segmentation algorithm to extract finger-vein network, which is further subject to thinning operation. Secondly, the resulting thinning image is taken as an input of a GAN model to restore the missed vein patterns. Thirdly, the minutiae points are extracted from restoration finger-vein pattern. Finally, we propose a matching approach for verification. Experimental results show that the proposed method can restore the missed vein pattern and reduce the equal error rate (EER) of the finger-vein verification system. INDEX TERMS Finger-vein recognition, vein restoration, generative adversarial network.

show abstract

Near‐Infrared Imaging Highly Enhanced by Pixel‐Level Integrated Plasmonic Metasurfaces on CMOS Image Sensors

Nan,

Zheng,

Dong

et al. 2024

Advanced Optical Materials

View full text Add to dashboard Cite

Near‐infrared (NIR) photodetection and imaging have sparked significant interests across a wide range of applications. While silicon photodiodes are commonly employed, the small light absorption coefficients of Si in NIR severely limit the performance, especially in the case of thin active Si layers. Although various light harvesting techniques are proposed to increase light absorption of Si, pixel‐level strategy for enhanced NIR imaging is still challenging in CMOS image sensors (CISs) with a pixel size in only a micron scale. In this paper, plasmonic metasurfaces are intimately integrated on top of 2.3 µm thick Si active regions of the pixels of a backside illumination (BI)‐CIS for NIR imaging for the first time. 200% improved photoresponsivity is obtained in experiments in such a planar Si layer rather than patterning the Si layer with potential damage to the active region. Numerical simulation results reveal highly enhanced light intensity in the thin active Si layer due to the presence of plasmonic metasurfaces. Significantly improved imaging brightness and signal‐to‐noise ratio of NIR imaging are demonstrated under both laser and LED illumination. This CMOS‐compatible technique is expected to hold promising potentials in applications including machine vision, iris certification, light detection and ranging (LiDAR), and optical communication in data centers.

show abstract

Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition

Cited by 134 publications

References 50 publications

Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net

Finger-Vein Pattern Restoration With Generative Adversarial Network

Near‐Infrared Imaging Highly Enhanced by Pixel‐Level Integrated Plasmonic Metasurfaces on CMOS Image Sensors

Contact Info

Product

Resources

About