IrisBeautyDet：Neural Network for Iris Localization and Cosmetic Contact Lens Detection

doi:10.3778/j.issn.1002-8331.2106-0460

Abstract

Abstract: Iris liveness detection is one of the important aspects involving security in iris recognition and one of the urgent problems in the field of iris recognition, where cosmetic contact lens detection is the most challenging area of iris liveness detection. This paper proposes a cosmetic contact lens detection algorithm IrisBeautyDet based on SSD（single shot multibox detector） object detection network, and lightens the network structure to significantly reduce the computation cost and substantially improve the speed by using MobileNet. Spatial attention and channel attention mechanisms are effective for the model to considerably improve accuracy. Experiments indicate that the algorithm has better generalization ability and robustness on the CASIA-Iris dataset and the University of Notre Dame NDCLD dataset of liveness and cosmetic contact lens iris data. Compared with the original SSD algorithm, IrisBeautyDet has fewer parameters and more prominent real-time performance. And the size of this model decreases from 91.1 MB to 26.1 MB, while increasing the detection speed from 29.68 frame/s to 41.88 frame/s. And the model’s classification precision achieves 99.21% and 98.61% for the live category and the cosmetic contact lens category. Guided-backpropagation is used to visualize the detection of feature map, analyze and optimize the model to make it more effective in extracting texture features of cosmetic contact lens.

Key words: cosmetic contact lens detection, iris liveness detection, presentation attack detection, attention mechanism, lightweight network, feature map visualization

摘要： 虹膜活体检测是虹膜识别中涉及安全的重要环节之一，也是虹膜识别领域亟待解决的问题之一，其中美瞳检测是虹膜活体检测中最具挑战性的领域。提出了一种基于SSD（single shot multibox detector）目标检测网络的虹膜定位和美瞳检测算法IrisBeautyDet，并对网络结构进行轻量化处理，引入MobileNet主干网络显著减少模型计算量，极大提高速度。采用空间注意力和通道注意力机制，进一步提高模型准确率。实验表明，在CASIA-Iris和圣母大学NDCLD的活体和美瞳虹膜数据集上，该算法具有较好的泛化能力和鲁棒性，相比原始SSD算法，IrisBeautyDet具有更少的参数量、更快的实时性和更高的准确率。相比原始SSD网络模型，该模型大小从91.1 MB下降到26.1 MB，同时将检测速度从29.68 frame/s提高到41.88 frame/s，对活体类和美瞳类的检测精确率达到99.21%和98.61%。利用导向反向传播（guided-backpropagation）对检测特征图进行可视化，分析并优化网络模型使其更有效地提取美瞳纹理特征。

关键词: 美瞳检测, 虹膜活体检测, 呈现攻击检测, 注意力机制, 轻量级网络, 特征图可视化

CHEN Xuqi, SHEN Wenzhong. IrisBeautyDet：Neural Network for Iris Localization and Cosmetic Contact Lens Detection[J]. Computer Engineering and Applications, 2023, 59(2): 120-128.

陈旭旗, 沈文忠. IrisBeautyDet：虹膜定位和美瞳检测网络[J]. 计算机工程与应用, 2023, 59(2): 120-128.

References

[1] DAS P，MCFIRATHT J，FANG Z，et al.Iris liveness detection competition （livdet-iris）-the 2020 edition[C]//2020 IEEE International Joint Conference on Biometrics（IJCB），2020：1-9.
[2] YAMBAY D，WALCZAK B，SCHUCKERS S，et al.LivDet-Iris 2015-iris liveness detection competition 2015[C]//IEEE International Conference on Identity，2017.
[3] DAUGMAN J.Wavelet demodulation codes，statistical independence，and pattern recognition[Z].Proc 2nd IMA-IP：Mathematical Methods，Algorithms，and Applications，2000：244-260.
[4] MCGRATH J，BOWYER K W，CZAJKA A.Open source presentation attack detection baseline for iris recognition[J].arXiv：1809.10172，2018.
[5] CZAJKA A，FANG Z，BOWYER K.Iris presentation attack detection based on photometric stereo features[C]//2019 IEEE Winter Conference on Applications of Computer Vision（WACV），2019：877-885.
[6] TROKIELEWICZ M，CZAJKA A，MACIEJEWICZ P.Presentation attack detection for cadaver iris[C]//2018 IEEE 9th International Conference on Biometrics Theory，Applications and Systems（BTAS），2018：1-10.
[7] SOLEYMANI S，DABOUEI A，DAWSON J，et al.Defending against adversarial iris examples using wavelet decomposition[C]//2019 IEEE 10th International Conference on Biometrics Theory，Applications and Systems（BTAS），2019：1-9.
[8] KUEHLKAMP A，PINTO A，ROCHA A，et al.Ensemble of multi-view learning classifiers for cross-domain iris presentation attack detection[J].IEEE Transactions on Information Forensics and Security，2018，14（6）：1419-1431.
[9] CZAJKA A.Pupil dynamics for iris liveness detection[J].IEEE Transactions on Information Forensics and Security，2015，10（4）：726-735.
[10] 宋平，黄玲，王云龙，等.基于计算光场成像的虹膜活体检测方法[J].自动化学报，2019，45（9）：1701-1712.
SONG P，HUANG L，WANG Y L，et al.Iris liveness detection based on light field imaging[J].Acta Automatica Sinica，2019，45（9）：1701-1712.
[11] 贾皓丽，沈建新，邢文元.基于Gabor滤波的虹膜活体检测[J].计算机应用与软件，2012，29（11）：137-138.
JIA H L，SHEN J X，XING W Y.Iris activity detection based on Gabor filter[J].Computer Applications and Software，2012，29（11）：137-138.
[12] 李志明.基于卷积神经网络的虹膜活体检测算法研究[J].计算机工程，2016，42（5）：239-243.
LI Z M.Research on iris liveness detection algorithm based on convolutional neural network[J].Computer Engineering，2016，42（5）：239-243.
[13] 刘明康，王宏民，李琦，等.增强型灰度图像空间实现虹膜活体检测[J].中国图象图形学报，2020，25（7）：1421-1435.
LIU M K，WANG H M，LI Q，et al.Enhanced gray-level image space for iris liveness detection[J].Journal of Image and Graphics，2020，25（7）：1421-1435.
[14] YAMBAY D，DOYLE J S，CZAJKA A，et al.LivDet-iris 2013—iris liveness detection competition 2013[C]//International Joint Conference on Biometrics，2014.
[15] YAMBAY D，BECKER B，KOHLI N，et al.LivDet iris 2017—iris liveness detection competition 2017[C]//2017 IEEE International Joint Conference on Biometrics（IJCB），2017：733-741.
[16] 周锐烨，沈文忠.PI-Unet：异质虹膜精确分割神经网络模型的研究[J].计算机工程与应用，2021，57（15）：223-229.
ZHOU R Y，SHEN W Z.PI-Unet：research on precise iris segmentation neural network model for heterogeneous iris[J].Computer Engineering and Applications，2021，57（15）：223-229.
[17] 晁静静，沈文忠，宋天舒.基于HOG和SVM的双眼虹膜图像的人眼定位算法[J].计算机工程与应用，2019，55（9）：184-189.
CHAO J J，SHEN W Z，SONG T S.Eye location algorithm of binocular iris image based on HOG and cascade SVM[J].Computer Engineering and Applications，2019，55（9）：184-189.
[18] 陈金鑫，沈文忠.基于EL-YOLO的虹膜图像人眼定位及分类算法[J].计算机工程与应用，2121，57（17）：217-223.
CHEN J X，SHEN W Z.Human eye localization and classification algorithm based on EL-YOLO[J].Computer Engineering and Applications，2121，57（17）：217-223.
[19] 滕童，沈文忠，毛云丰.基于级联神经网络的多任务虹膜快速定位方法[J].计算机工程与应用，2020，56（12）：118-124.
TENG T，SHEN W Z，MAO Y F.Multi-task iris fast location method based on cascaded neural network[J].Computer Engineering and Applications，2020，56（12）：118-124.
[20] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[21] HOWARD A G，ZHU M，CHEN B，et al.Mobilenets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[22] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.

[23] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.

[24] SPRINGENBERG J T，DOSOVITSKIY A，BROX T，et al. Striving for simplicity：the all convolutional net[J].arXiv：1412.6806，2014.