Abstract
Iris detection remains vital application value in computer vision. Although the considerable advances and successes have been achieved by utilizing deep convolutional neural networks for iris detection, directly locating a small proportion of the iris from the full facial images still confronts considerable challenges. In this study, we proposed the YOLO NFPEM network, which employing the Feature Pyramid Enhancement Module (FPEM) cascaded to enhance and merge the different scale features (52 × 52, 26 × 26, 13 × 13) from the PEP7 layer (52 × 52), PEP15 layer (26 × 26) and PEP17 layer (13 × 13) of YOLO Nano network. YOLO NFPEM was train and tested on our presented multi-scale eye dataset (MSED) which contains full and partial facial images, and left/ right eye images. The results shown that YOLO NFPEM with three PEP modules cascaded achieves the best AP for iris of ~ 91.37% higher than YOLO Nano (~83.99%), YOLO Nano with enhanced FPN cascaded and the other YOLO NFPEM architectures, while still reaching a mAP of ~ 84.62%. Furthermore, we found an irreconcilable contradiction, considering the memory consumption and computational cost, neither the enhanced FPN nor FPEM module cascaded can achieve the best performance on both mAP and AP of iris. Testing results also shown that the small-size feature extraction and fusion capabilities of PEP modules cascaded are more powerful than FPN and enhanced FPN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tong, K., Wu, Y., Zhou, F.: Recent advances in small object detection based on deep learning: A review. Image Vis. Comput. 97 (2020), https://doi.org/10.1016/j.imavis.2020.103910
Sandler, M., Howard, A., Zhu, M., et al.: MobileNetV2: Inverted Residuals and Linear Bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018) https://doi.org/10.1109/CVPR.2018.00474.
Wong, A., Famuori, M., Shafiee, M.J., et al.: YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection. arXiv:1910.01271
Deng, C., Wang, M., Liu, L., et al.: Extended Feature Pyramid Network for Small Object Detection. arXiv: 2003.07021v2
Zhang, Y., Bai, Y., Ding, M., Ghanem, B.: Multi-task generative adversarial network for detecting small objects in the wild. Int. J. Comput. Vision 128(6), 1810–1828 (2020). https://doi.org/10.1007/s11263-020-01301-6
Kisantal, M., Wojna, Z.,Murawski, J., et al.: Augmentation for small object detection. (2019) arXiv: 1902.07296v1
Buda, M., Maki, A., Mazurowski, M.A.: A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249–259 (2018)
Lin, T., Dollár, P., Girshick, R., et al.: Feature Pyramid Networks for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944, 2017, https://doi.org/10.1109/CVPR.2017.106.
Wang, W., Xie, E., Song, X., et al.: Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8439–8448 (2019) https://doi.org/10.1109/ICCV.2019.00853.
Zhang, S., Zhu, X., Lei, Z., et al.: S^3FD: single shot scale-invariant face detector. IEEE Int. Conf. Comput. Vis. (ICCV) 2017, 192–201 (2017). https://doi.org/10.1109/ICCV.2017.30
Zhang, W., Wang, S., Thachan, S., Chen, J., Qian, Y.: Deconv R-CNN for Small Object Detection on Remote Sensing Images. In: IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018, pp. 2483–2486, https://doi.org/10.1109/IGARSS. 2018.8517436.
Singh, B., Davis, L.S.: An analysis of scale invariance in object detection - SNIP. IEEE/CVF Conf. Comput. Vis. Patt. Recogn. 2018, 3578–3587 (2018). https://doi.org/10.1109/CVPR.2018.00377
Singh, B., Najibi & L.y S. Davis.: SNIPER: Efficient Multi-Scale Training. In: NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Dec. 2018, pp. 9333–9343 (2018)
Kim, Y., Kang, B., Kim, D.: “SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection”, 15th European Conference of Computer Vision, pp. 328–343. Munich, Germany (2018)
Wang, X., Shrivastava, A., Gupta, A.: A-fast-RCNN: hard positive generation via adversary for object detection. IEEE Conf. Comput. Vis. Patt. Recogn. (CVPR) 2017, 3039–3048 (2017). https://doi.org/10.1109/CVPR.2017.324
Grel, T.: Region of interest pooling explained. https://deepsense.ai/region-of-interest-pooling-explained/ (2017)
Hu, X., Xu, X., Xiao, Y., et al.: SINet: A scale-insensitive convolutional neural network for fast vehicle detection. IEEE Trans. Intell. Transp. Syst. 20(3), 1010–1019 (2019). https://doi.org/10.1109/TITS.2018.2838132
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. IEEE Conf. Comput. Vis. Patt. Recogn. (CVPR) 2016, 779–788 (2016). https://doi.org/10.1109/CVPR.2016.91
Soltanolkotabi, M., Javanmard, A., Lee, J.D.: Theoretical insights into the optimization landscape of over-parameterized shallow neural networks. IEEE Trans. Inf. Theor. 65(2), 742–769 (2019). https://doi.org/10.1109/TIT.2018.2854560
Chen, S., Li, Z., Tang, Z.: Relation R-CNN: a graph based relation-aware network for object detection. IEEE Signal Process. Lett. 27, 1680–1684 (2020). https://doi.org/10.1109/LSP.2020.3025128
Tang, X., Du, D.K., He, Z., Liu, J.: PyramidBox: A Context-Assisted Single Shot Face Detector. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 812–828. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_49
Gregor, K., Danihelka, I., Graves, A., et al.: DRAW: A Recurrent Neural Network for Image Generation. In: ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 1462–1471 (2015)
Sak, H., Senior, A., Beaufays, F.: Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. Comput. Sci. 338–342, (2014)
Xi, Y., Zheng, J., He, X., et al.: Beyond context: exploring semantic similarity for small object detection in crowded scenes. Patt. Recogn. Lett. 137, 53–60 (2020). https://doi.org/10.1016/j.patrec.2019.03.009
Xing, C., Liang, X., Bao, Z.: A Small Object Detection Solution by Using Super- Resolution Recovery. In: 2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT), 2019, pp. 313–316, https://doi.org/10.1109/ICCSNT47585.2019.8962422
Li, Y., Dong, H., Li, H., et al.: Multi-block SSD based on small object detection for UAV railway scene surveillance. Chin. J. Aeronaut. 33(6), 1747–1755 (2020)
Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. IEEE Conf. Comput. Vis. Patt. Recogn. (CVPR) 2017, 1951–1959 (2017). https://doi.org/10.1109/CVPR.2017.211
Liang, X., Zhang, J., Zhuo, L., et al.: Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1758–1770 (2020). https://doi.org/10.1109/TCSVT.2019.2905881
Fang, P., Shi, Y.: Small Object Detection Using Context Information Fusion in Faster R-CNN. In: 2018 IEEE 4th International Conference on Computer and Communications (ICCC), 2018, pp. 1537–1540, https://doi.org/10.1109/Comp Comm.2018.8780579
Bosquet, B., Mucientes, M., Brea, V.M.: STDnet: Exploiting high resolution feature maps for small object detection. Eng. Appl. Artif. Intell. 91, (2020) https://doi.org/10.1016/j.engappai.2020.103615
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. IEEE Conf. Comput. Vis. Patt. Recogn. (CVPR) 2017, 6517–6525 (2017). https://doi.org/10.1109/CVPR.2017.690
Wang, C., Zhu, Y., Liu, Y., et al.: Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework (2019) arXiv:1901.11195
Lee, Y., Kim, K., Hoang, T., et al.: Deep Residual CNN-based ocular recognition based on rough pupil detection in the images by NIR camera sensor. Sensors 19(4), 842–872 (2019). https://doi.org/10.3390/s19040842
Minaee, S., Abdolrashidi, A.: DeepIris: Iris Recognition Using A Deep Learning Approach (2019) arXiv:1907.09380
Miron, C., Pasarica, A., Bozomitu, R.G., et al.: Efficient pupil detection with a convolutional neural network. E-Health Bioeng. Conf. (EHB) 2019, 1–4 (2019). https://doi.org/10.1109/EHB47216.2019.8969984
Feng, C., Sun, Y., Li, X.: Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment (2019) arXiv:1903.10140
Proença, H., Neves, J.C.: Segmentation-less and non-holistic deep-learning frameworks for iris recognition. IEEE/CVF Conf. Comput. Vis. Patt. Recogn. Workshops (CVPRW) 2019, 2296–2305 (2019). https://doi.org/10.1109/CVPRW.2019.00283
Trokielewicz, M., Czajka, A., Maciejewicz, P.: Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation. Vol. 94, Feb. 2020, https://doi.org/10.1016/j.imavis.2019.103866
Gangwar, A., Joshi, A., Joshi, P., et al.: DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition (2019) arXiv:1902.05390
Hassan, B., Ahmed, R., Hassan, T., et al.: SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression (2020) arXiv:2003.00825
Rot, P., Emeršič, Ž, Struc, V., Peer, P.: Deep multi-class eye segmentation for ocular biometrics. IEEE Int. Work Conf. Bioinspired Intell. (IWOBI) 2018, 1–8 (2018). https://doi.org/10.1109/IWOBI.2018.8464133
Wolfgang, F., Thiago, S., Gjergji, K., et al.: PupilNet: Convolutional Neural Networks for Robust Pupil Detection (2020) arXiv:1601.04902
Han, S.Y., Kim, Y., Lee, S.H., Cho, N.I.: Pupil Center Detection Based on the UNet for the User Interaction in VR and AR Environments. In: 2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR), 2019, pp. 958–959, https://doi.org/10.1109/VR.2019.8798027
He, F., Han, Y., Wang, H., et al.: Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network. J. Electron. Imag. 26(2), (2017) https://doi.org/10.1117/1.JEI.26.2.023005
Joseph, R., Ali, F.: YOLOv3: An Incremental Improvement (2018) arXiv:1804.02767
Wu, D., Lv, S., Jiang, M., et al: Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Comput. Electron. Agricul. 178, 2020, https://doi.org/10.1016/j.compag.2020.105742
Chen, W., Huang, H., Peng, S., Zhou, C., Zhang, C.: YOLO-face: a real-time face detector. Vis. Comput. 37(4), 805–813 (2020). https://doi.org/10.1007/s00371-020-01831-7
Proenca, H., Filipe, S., Santos, R., Oliveira, J., Alexandre, L.A.: The UBIRIS.v2: A database of visible wavelength iris images captured on-the-move and at-a-distance. IEEE Trans. Patt. Anal. Mach. Intell. 32(8), 1529–1535 (2010). https://doi.org/10.1109/TPAMI.2009.66
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ge, X. et al. (2023). YOLO NFPEM: A More Accurate Iris Detector. In: Degen, H., Ntoa, S. (eds) Artificial Intelligence in HCI. HCII 2023. Lecture Notes in Computer Science(), vol 14051. Springer, Cham. https://doi.org/10.1007/978-3-031-35894-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-35894-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35893-7
Online ISBN: 978-3-031-35894-4
eBook Packages: Computer ScienceComputer Science (R0)