Abstract
Morphing attacks presented by image and/or feature information of more than one individual are a major concern of biometric systems. Penetrating the morphed biometric information to biometric recognition systems may cause successful verification of all presented individuals to the morphed image against a registered template. Therefore, designing a robust biometric system to detect this kind of attack is necessary. This paper aims to implement a novel solution for distinguishing the morph and bona fide identities using a hybrid detection system for face-iris biometrics. The anti-morphing pipeline concentrates on two steps of detection using handcrafted and deep-learning techniques. Firstly, the detection is done according to the texture information of images and then the morphing attack detection framework is applied once more for images recognized as bona fide using deep learning technique to boost the reliability of the face-iris biometric systems. The effectiveness of proposed morph detection method is examined on FERET, FRGC, and FRLL morph datasets using three different morphing algorithms for face biometric. In order to testify the robustness of proposed anti-morphing technique, CASIAv4-Interval database is used on one morphing algorithm for iris biometric. Demonstration of results clarifies the robustness of the proposed solution for morph detection.
Similar content being viewed by others
Data availability
The datasets and tools are available publicly athttps://www.idiap.ch/en/dataset/feret-morphs, https://www.idiap.ch/en/dataset/frll-morphs, https://www.idiap.ch/en/dataset/frgc-morphs, and http://biometrics.idealtest.org.
OpenCV https://www.learnopencv.com/face-morph-using-opencv-cpp-python/), FaceMorpher (https://github.com/yaopang/FaceMorpher/tree/master/facemorpher).
StyleGAN 2, (https://github.com/NVlabs/stylegan2).
References
Agarwal A, Singh R, Vatsa M et al (2017) SWAPPED! Digital face presentation attack detection via weighted local magnitude pattern. Proc. of the 2017 Int. Joint Conf. on Biometrics (IJCB), Denver, CO, USA
Agarwal A, Singh R, Vatsa M, Noore A (2021) MagNet: detecting digital presentation attacks on face recognition. Front Artif Intell 4:643424
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27
Chinese Academy of Sciences’ Institute of Automation. CASIA Iris Image Database V4.0 – Interval. http://biometrics.idealtest.org
Damer N, Saladie AM, Braun A et al (2018) MorGAN: recognition vulnerability and attack detectability of face morphing attacks created by generative adversarial network. Proc. of the 9th IEEE Int. Conf. on Biometrics: Theory, Applications, and Systems (BTAS), Los Angeles, CA, USA
Damer N, Zienert S, Wainakh Y et al (2019) A multi-detector solution towards an accurate and generalized detection of face morphing attacks. Proc. of the 22nd Int. Conf. on Information Fusion (FUSION), Ottawa, Canada
Damer N, Spiller N, Fang M, Boutros F, Kirchbuchner F, Kuijper A (2021) PW-MAD: pixel-wise supervision for generalized face morphing attack detection. International symposium on visual computing. Springer, pp 291–304
Debiasi L, Rathgeb C, Scherhag U et al (2018) PRNU variance analysis for morphed face image detection’. Proc. of the 9th IEEE Int. Conf. on Biometrics: Theory, Applications, and Systems (BTAS), Los Angeles, CA, USA
Debiasi L, Scherhag U, Rathgeb C et al (2018) PRNU-based detection of morphed face images. Proc. of the 6th Int. Workshop on Biometrics and Forensics (IWBF), Sassari, Italy
Debiasi L, Damer N, Saladié AM et al (2019) On the detection of GAN-based face morphs using established morph detectors. Proc. of the 20th Int. Conf. on Image Analysis and Processing (ICIAP), Trento, Italy
Elaggoune H, Belahcene M, Bourennane S (2022) Hybrid descriptor and optimized CNN with transfer learning for face recognition. Multimed Tools Appl 81:9403–9427. https://doi.org/10.1007/s11042-021-11849-1
Eskandari M, Önsen T (2015) Selection of optimized features and weights on face-iris fusion using distance images. Comput Vis Image Underst 137:63–75
Eskandari M, Toygar Ö (2015) Selection of optimized features and weights on face-iris fusion using distance images. Comput Vis Image Underst 137:63–75
Eskandari M, Sharifi O (2016) Optimum scheme selection for face–iris biometric. IET Biom 6:334–341
Eskandari M, Sharifi O (2019) Effect of face and ocular multimodal biometric systems on gender classification. IET Biom 8(4):243–248
Fang M et al (2021) Cross-database and cross-attack Iris presentation attack detection using micro stripes analyses. Image Vis Comput 105:104057
Ferrara M, Franco A, Maltoni D (2019) Decoupling texture blending and shape warping in face morphing. 2019 International Conference of the Biometrics Special Interest Group (BIOSIG). IEEE
Ferrara M, Franco A, Maltoni D (2019) Face morphing detection in the presence of printing/scanning and heterogeneous image sources. CoRR, 2019, abs/1901.08811. Available at: http://arxiv.org/abs/1901.08811
Hamza M, Tehsin S, Humayun M, Almufareh MF, Alfayad M (2022) A comprehensive review of face morph generation and detection of fraudulent identities. Appl Sci 12(24):12545
Jassim S, Asaad A (2018) Automatic detection of image morphing by topology-based analysis. 2018 26th European Signal Processing Conference (EUSIPCO). IEEE
King ED (2009) Dlib-ml: a machine learning toolkit”. J Mach Learn Res 10:1755–1758
Korshunov P, Marcel S (2019) Vulnerability of face recognition to deep morphing. arXiv preprint arXiv:1910.01933
Mallick S (2016) Face morph using opencv — c++ / python
Masek L, Koves P (2003) MATLAB Source code for a biometric identification system based on iris patterns. The University of Western Australia, The School of Computer Science and Software Engineering
Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measure with classification based on feature distributions. Pattern Recognit 29:51–59
Phillips PJ et al (1998) The FERET database and evaluation procedure for face-recognition algorithms. Image Vis Comput 16(5):295–306
Phillips PJ et al (2005) Overview of the face recognition grand challenge. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), vol 1. IEEE
Quek A (2019) Facemorpher
Raghavendra R, Raja KB, Busch C (2016) Detecting morphed face images’. Proc. of the 8th Int. Conf. on Biometrics Theory, Applications and Systems (BTAS), New York, NY, USA
Raghavendra R et al (2017) Face morphing versus face averaging: vulnerability and detection. 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE
Raja K, Venkatesh S, Christoph Busch RB (2017) Transferable deep-cnn features for detecting digital and print-scanned morphed face images. Proceedings of the IEEE conference on computer vision and pattern recognition workshops
Raja K, Gupta G, Venkatesh S, Ramachandra R, Busch C (2022) Towards generalized morphing attack detection by learning residuals. Image Vis Comput 126:104535
Ramachandra R et al (2019) Towards making morphing attack detection robust using hybrid scale-space colour texture features. 2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA). IEEE
Rathgeb C, Busch C (2017) On the feasibility of creating morphed iris-codes. 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE
Salih ZA, Thabit R, Zidan KA, Khoo BE (2022) Challenges of face image authentication and suggested solutions. In: 2022 International Conference on Information Technology Systems and Innovation (ICITSI). IEEE, pp 189–193
Sarkar E et al (2021) Vulnerability analysis of face morphing attacks from landmarks and generative adversarial networks. arXiv preprint arXiv:2012.05344. ICASSP 2021
Scherhag U, Raghavendra R, Raja KB et al (2017) On the vulnerability of face recognition systems towards morphed face attacks. Proc. of the 5th Int. Workshop on Biometrics and Forensics (IWBF), Coventry, UK
Scherhag U, Rathgeb C, Busch C (2018) Performance variation of morphed face image detection algorithms across different datasets. Proc. of the 6th Int. Workshop on Biometrics and Forensics (IWBF), Sassari, Italy
Scherhag U, Rathgeb C, Busch C (2018) Towards detection of morphed face images in electronic travel documents. Proc. of the 13th IAPR Workshop onDocument Analysis Systems (DAS), Vienna, Austria
Scherhag U, Debiasi L, Rathgeb C et al (2019) Detection of face morphing attacks based on PRNU analysis. IEEE Trans Biom Behav Identity Sci 1:302–317
Scherhag U et al (2020) Face morph detection for unknown morphing algorithms and image sources: a multi-scale block local binary pattern fusion approach. IET Biom 9(6):278–289
Scherhag U, Rathgeb C, Merkle J et al (2019) Face recognition systems under morphing attacks: a survey. IEEE Access 7:23012–23026
Seibold C et al (2017) Detection of face morphing attacks by deep learning. International workshop on digital watermarking. Springer, Cham
Seibold C, Hilsmann A, Eisert P (2018) Reflection analysis for face morphing attack detection. Proc. of the 26th European Signal Processing Conf. (EUSIPCO), Rome, Italy
Seibold C, Samek W, Hilsmann A, Eisert P (2020) Accurate and robust neural networks for face morphing attack detection. J Inf Secur Appl 53:102526
Sharifi O, Eskandari M, Yildiz MÇ (2017) Scheming an efficient facial recognition system using global and random local feature extraction methods. In: Proceedings of the 2017 International Conference on Computer Science and Engineering (UBMK), Antalya, Turkey, 5–8 October 201.
Sharma R, Ross A (2021) Image-level iris morph attack. 2021 IEEE International Conference on Image Processing (ICIP). IEEE
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Spreeuwers L, Schils M, Veldhuis R (2018) Towards robust evaluation of face morphing detection. 2018 26th European Signal Processing Conference (EUSIPCO). IEEE
Tapia JE, Claudio AP, Kevin WB (2014) Gender classification from iris images using fusion of uniform local binary patterns. In: Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 6–9 September 2014. Springer, Cham
Wandzik L, Kaeding G, Garcia RV (2018) Morphing detection using a general-purpose face recognition system. 2018 26th European Signal Processing Conference (EUSIPCO). IEEE
Yildiz MC, Sharifi O, Eskandari M (2016) Log-Gabor transforms and score fusion to overcome variations in appearance for face recognition. In: Proceedings of the international conference on computer vision and graphics, Warsaw, Poland, 19–20 September 2016. Springer, Cham
Zhang L-B, Peng F, Long M (2018) Face morphing detection using Fourier spectrum of sensor pattern noise. 2018 IEEE Int. Conf. on Multimedia and Expo (ICME), San Diego, CA, USA
Zymkowski M, Jasiński P, Saeed K (2021) Iris-based human identity recognition with machine learning methods and discrete fast Fourier transform. Innov Syst Softw Eng 17:309–317. https://doi.org/10.1007/s11334-021-00392-9
Author information
Authors and Affiliations
Contributions
Not applicable.
Corresponding author
Ethics declarations
Conflicts of interest
No conflict of interest.
Competing interests
not applicable
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sharifi, O. Two-stage morph detection scheme for face and iris biometrics. Multimed Tools Appl 82, 43013–43028 (2023). https://doi.org/10.1007/s11042-023-15375-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15375-0