Periocular authentication in smartphones applying uLBP descriptor on CNN Feature Maps

• William Barcellos USP
• Adilson Gonzaga USP

DOI: https://doi.org/10.5753/wvc.2021.18890

Resumo

The outputs of CNN layers, called Activations, are composed of Feature Maps, which show textural information that can be extracted by a texture descriptor. Standard CNN feature extraction use Activations as feature vectors for object recognition. The goal of this work is to evaluate a new methodology of CNN feature extraction. In this paper, instead of using the Activations as a feature vector, we use a CNN as a feature extractor, and then we apply a texture descriptor directly on the Feature Maps. Thus, we use the extracted features obtained by the texture descriptor as a feature vector for authentication. To evaluate our proposed method, we use the AlexNet CNN previously trained on the ImageNet database as a feature extractor; then we apply the uniform LBP (uLBP) descriptor on the Feature Maps for texture extraction. We tested our proposed method on the VISOB dataset composed of periocular images taken from 3 different smartphones under 3 different lighting conditions. Our results show that the use of a texture descriptor on CNN Feature Maps achieves better performance than computer vision handcrafted methods or even by standard CNN feature extraction.

Palavras-chave: CNN, Feature Maps, smartphone, periocular authentication, AlexNet, VISOB

Referências

Gupta, S.; Buriro, A. and Crispo, B., 2018. Demystifying Authentication Concepts in Smartphones: Ways and Types to Secure Access. Mobile Information Systems, 2018, pp.1-16.

Sharif, M.; Naz, F.; Yasmin, M.; Shahid, M. and Rehman, A., 2017. Face Recognition: A Survey. Journal of Engineering Science and Technology Review, 10(2), pp.166-177.

Alonso-Fernandez, F. and Bigun, J., 2016. A survey on periocular biometrics research. Pattern Recognition Letters, 82, pp.92-105.

Smereka, J. M.; Boddeti, V. N. and Kumar, B. V., "Probabilistic Deformation Models for Challenging Periocular Image Verification," in IEEE Transactions on Information Forensics and Security, vol. 10, no. 9, pp. 1875-1890, Sept. 2015, doi: 10.1109/TIFS.2015.2434271.

Mahalingam, G.; Ricanek, K. and Albert, A M., "Investigating the Periocular-Based Face Recognition Across Gender Transformation," in IEEE Transactions on Information Forensics and Security, vol. 9, no. 12, pp. 2180-2192, Dec. 2014, doi: 10.1109/TIFS.2014.2361479.

Juefei-Xu, F.; Luu, K.; Savvides, M.; Bui, T. and Suen, C.; 2011. Investigating age invariant face recognition based on periocular biometrics. 2011 International Joint Conference on Biometrics (IJCB),.

Lecun, Y.; Bottou, L.; Bengio, Y. and Haffner, P., "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.

Krizhevsky, A.; Sutskever, I. and Hinton, G., 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), pp.84-90.

Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; Berg, A. and Fei-Fei, L., 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115(3), pp.211-252.

He, K.; Zhang, X.; Ren, S. and Sun, J., "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.

Girshick, R.; Donahue, J.; Darrell, T. and Malik, J., "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580-587, doi: 10.1109/CVPR.2014.81.

Hariharan, B.; Arbeláez, P.; Girshick, R. and Malik, J., 2014. Simultaneous Detection and Segmentation. Computer Vision - ECCV 2014, pp.297-312.

Zhou, B.; Lapedriza, A.; Khosla, A.; Oliva, A. and Torralba, A., "Places: A 10 Million Image Database for Scene Recognition," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 6, pp. 1452-1464, 1 June 2018, doi: 10.1109/TPAMI.2017.2723009.

Razavian, A. S.; Azizpour, H.; Sullivan, J. and Carlsson, S., "CNN Features Off-the-Shelf: An Astounding Baseline for Recognition," 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014, pp. 512-519, doi: 10.1109/CVPRW.2014.131.

Raja, K. B.; Raghavendra, R.; Stokkenes, M. and Busch, C., "Smartphone authentication system using periocular biometrics," 2014 International Conference of the Biometrics Special Interest Group (BIOSIG), 2014, pp. 1-8.

Raja, K.; Raghavendra, R. and Busch, C., 2016. “Collaborative representation of deep sparse filtered features for robust verification of smartphone periocular images.” 2016 IEEE International Conference on Image Processing (ICIP),.

Raghavendra, R. and Busch, C., 2016. Learning deeply coupled autoencoders for smartphone based robust periocular verification. 2016 IEEE International Conference on Image Processing (ICIP),.

Ahuja, K.; Bose, A.; Nagar, S.; Dey, K. and Barbhuiya, F., 2016. ISURE: User authentication in mobile devices using ocular biometrics in visible spectrum. 2016 IEEE International Conference on Image Processing (ICIP),.

Rattani, A.; Derakhshani, R.; Saripalle, S. and Gottemukkula, V., 2016. ICIP 2016 competition on mobile ocular biometric recognition. 2016 IEEE International Conference on Image Processing (ICIP),.

Raja, K.; Raghavendra, R.; Stokkenes, M. and Busch, C., 2015. Multi-modal authentication system for smartphones using face, iris and periocular. 2015 International Conference on Biometrics (ICB),.

Santos, G.; Grancho, E.; Bernardo, M. and Fiadeiro, P., 2015. Fusing iris and periocular information for cross-sensor recognition. Pattern Recognition Letters, 57, pp.52-59.

Ahmed, N.; Cvetkovic, S.; Siddiqi, E.; Nikiforov, A. and Nikiforov, I., 2016. Using fusion of iris code and periocular biometric for matching visible spectrum iris images captured by smart phone cameras. 2016 23rd International Conference on Pattern Recognition (ICPR),.

Alonso-Fernandez, F.; Raja, K.; Busch, C. and Bigun, J., 2017. Log-likelihood score level fusion for improved cross-sensor smartphone periocular recognition. 2017 25th European Signal Processing Conference (EUSIPCO),.

Stokkenes, M.; Ramachandra, R.; Raja, K.; Sigaard, M. and Busch, C., 2017. Feature level fused templates for multi-biometric system on smartphones. 2017 5th International Workshop on Biometrics and Forensics (IWBF),.

Aginako, N.; Castrillón-Santana, M.; Lorenzo-Navarro, J.; Martínez-Otzeta, J. and Sierra, B., 2017. Periocular and iris local descriptors for identity verification in mobile applications. Pattern Recognition Letters, 91, pp.52-59.

Rattani, A. and Derakhshani, R., 2017. On fine-tuning convolutional neural networks for smartphone based ocular recognition. 2017 IEEE International Joint Conference on Biometrics (IJCB),.

Ahuja, K.; Islam, R.; Barbhuiya, F. and Dey, K., 2017. Convolutional neural networks for ocular smartphone-based biometrics. Pattern Recognition Letters, 91, pp.17-26.

Reddy, N.; Rattani, A. and Derakhshani, R., 2018. Comparison of Deep Learning Models for Biometric-based Mobile User Authentication. 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS),.

Rattani, A.; Reddy, N. and Derakhshani, R., 2018. Multi-biometric Convolutional Neural Networks for Mobile User Authentication. 2018 IEEE International Symposium on Technologies for Homeland Security (HST),.

Kondapi, L.; Rattani, A. and Derakhshani, R., 2019. Cross-illumination Evaluation of Hand Crafted and Deep Features for Fusion of Selfie Face and Ocular Biometrics. 2019 IEEE International Symposium on Technologies for Homeland Security (HST),.

De Marsico, M.; Nappi, M. and Proença, H., 2017. Results from MICHE II - Mobile Iris CHallenge Evaluation II. Pattern Recognition Letters, 91, pp.3-10.

Dertat, A., 2017. Applied Deep Learning - Part 4: Convolutional Neural Networks. [online] Towards Data Science. Available at: [link]. [Accessed 27 September 2021].