Abstract
This work proposes a fully convolutional network architecture for RGB face image generation from a given input thermal face image to be applied in face recognition scenarios. The proposed method is based on the FusionNet architecture and increases robustness against overfitting using dropout after bridge connections, randomised leaky ReLUs (RReLUs), and orthogonal regularization. Furthermore, we propose to use a decoding block with resize convolution instead of transposed convolution to improve final RGB face image generation. To validate our proposed network architecture, we train a face classifier and compare its face recognition rate on the reconstructed RGB images from the proposed architecture, to those when reconstructing images with the original FusionNet, as well as when using the original RGB images. As a result, we are introducing a new architecture which leads to a more accurate network.
Similar content being viewed by others
References
Aitken A, Ledig C, Theis L, Caballero J, Wang Z, Shi W (2017) Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize, arXiv:1707.02937
Anbarjafari G, Demirel H (2011) Modern: Face recognition. VDM Publishing
Anbarjafari G (2013) Face recognition using color local binary pattern from mutually independent color channels. EURASIP J Image Video Process 2013(1):6
Anbarjafari G, Haamer RE, Lusi I, Tikk T, Valgma L (2018) 3D face reconstruction with region based best fit blending using mobile phone for virtual reality based social media. Bulletin of the Polish Academy of Sciences Technical Sciences
Bebis G, Gyaourova A, Singh S, Pavlidis I (2006) Face recognition by fusing thermal infrared and visible imagery. Image Vis Comput 24(7):727–742
Bourlai T, Hornak LA (2016) Face recognition outside the visible spectrum. Image Vis Comput 55:14–17
Brock A, Lim T, Ritchie JM, Weston N (2016) Neural photo editing with introspective adversarial networks, arXiv:1609.07093
Buddharaju P, Pavlidis IT, Tsiamyrtzis P, Bazakos M (2007) Physiology-based face recognition in the thermal infrared spectrum. IEEE Trans Pattern Anal Mach Intell 29(4):613–626
Daneshmand M, Helmi A, Avots E, Noroozi F, Alisinanoglu F, Arslan HS, Gorbova J, Haamer RE, Ozcinar C, Anbarjafari G (2018) 3D Scanning: A comprehensive survey, arXiv:1801.08863
Demirel H, Anbarjafari G (2008) Pose invariant face recognition using probability distribution functions in different color channels. IEEE Signal Process Lett 15:537–540
Demirel H, Anbarjafari G, Jahromi MNS (2008) Image equalization based on singular value decomposition. In: 2008. ISCIS’08. 23rd International Symposium on Computer and Information Sciences. IEEE, pp 1–5
Friedrich G, Yeshurun Y (2002) Seeing people in the dark: face recognition in infrared images. In: Biologically Motivated Computer Vision. Springer, pp 348–359
Ghiass RS, Arandjelović O, Bendada A, Maldague X (2014) Infrared face recognition: a comprehensive review of methodologies and databases. Pattern Recogn 47(9):2807–2824
Gross R, Matthews I, Baker S (2006) Active appearance models with occlusion. Image Vis Comput 24(6):593–604
Guo J, Lei Z, Wan J, Avots E, Hajarolasvadi N, Knyazev B, Kuharenko A, Junior JCSJ, Baró X, Demirel H, Allik J, Anbarjafari G (2018) Dominant and complementary emotion recognition from still images of faces. IEEE Access 6:26 391–26 403
Haamer RE, Kulkarni K, Imanpour N, Haque MA, Avots E, Breisch M, Nasrollahi K, Escalera S, Ozcinar C, Baro X et al (2018) Changes in facial expression as biometric: a database and benchmarks of identification. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE, pp 621–628
Hsieh C-C, Hsih M-H, Jiang M-K, Cheng Y-M, Liang E-H (2016) Effective semantic features for facial expressions recognition using svm. Multimed Tools Appl 75(11):6663–6682
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456
Jain A, Ross A, Prabhakar S (2004) An introduction to biometric recognition. IEEE Trans Circ Syst Video Technol 14(1):4–20
Kulkarni K, Corneanu C, Ofodile I, Escalera S, Baró X, Hyniewska S, Allik J, Anbarjafari G (2018), Automatic recognition of facial displays of unfelt emotions. IEEE Transactions on Affective Computing
Lin W-Y, Chen M-Y (2014) A novel framework for automatic 3d face recognition using quality assessment. Multimed Tools Appl 68(3):877–893
Liu M, Wang R, Li S, Shan S, Huang Z, Chen X (2014) Combining multiple kernel methods on riemannian manifold for emotion recognition in the wild. In: Proceedings of the 16th International Conference on Multimodal Interaction. ACM, pp 494–501
Liu J, Liu W, Ma S, Lu C, Xiu X, Pathirage N, Li L, Chen G, Zeng W (2018) Face recognition based on manifold constrained joint sparse sensing with k-svd. Multimedia Tools and Applications 77(21):28863–28883
Nikisins O, Nasrollahi K, Greitans M, Moeslund TB (2014) Rgb-dt based face recognition. In: 2014 22nd International Conference on Pattern Recognition (ICPR). IEEE, pp 1716–1721
Nixon MS, Correia PL, Nasrollahi K, Moeslund TB, Hadid A, Tistarelli M (2015) On soft biometrics. Pattern Recogn Lett 68:218–230
Odena A, Dumoulin V, Olah C (2016) Deconvolution and checkerboard artifacts. Distill 1(10):e3
Parkhi OM, Vedaldi A, Zisserman A (2015) Deep face recognition, vol 1
Quan TM, Hilderbrand DG, Jeong W-K (2016) Fusionnet: A deep fully residual convolutional neural network for image segmentation in connectomics, arXiv:1612.05360
Sajjadi MS, Scholkopf B, Hirsch M (2017) Enhancenet: Single image super-resolution through automated texture synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4491–4500
Sarfraz MS, Stiefelhagen R (2015) Deep perceptual mapping for thermal to visible face recognition, arXiv:1507.02879
Saxe AM, McClelland JL, Ganguli S (2013) Exact solutions to the nonlinear dynamics of learning in deep linear neural networks, arXiv preprint arXiv:1312.6120
Shi W, Caballero J, Huszár F, Totz J, Aitken A, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1874–1883
Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C (2015) Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 648–656
van Laarhoven T (2017) L2 regularization versus batch and weight normalization, arXiv:1706.05350
Wan J, Escalera S, Baro X, Escalante HJ, Guyon I, Madadi M, Allik J, Gorbova J, Anbarjafari G (2017) Results and analysis of chalearn lap multi-modal isolated and continuous gesture recognition, and real versus fake expressed emotions challenges. In: Chalearn lap, action, gesture, and emotion recognition workshop and competitions: Large scale multimodal gesture recognition and real versus fake expressed emotions, ICCV, vol 4, no 6
Wilson AC, Roelofs R, Stern M, Srebro N, Recht B (2017) The marginal value of adaptive gradient methods in machine learning. In: Advances in Neural Information Processing Systems, pp 4151–4161
Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network, arXiv:1505.00853
Zeiler MD, Krishnan D, Taylor GW, Fergus R (2010) Deconvolutional networks. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 2528–2535
Zhang H, Patel VM, Riggan BS, Hu S (2017) Generative adversarial network-based synthesis of visible faces from polarimetrie thermal faces. In: 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE, pp 100–107
Zhang T, Wiliem A, Yang S, Lovell B (2018) Tv-gan: Generative adversarial network based thermal to visible face recognition. In: 2018 International Conference on Biometrics (ICB). IEEE, pp 174–181
Acknowledgments
This work has been partially supported by IT Academy/StudyITin.ee, the Scientific and Technological Research Council of Turkey (TUBITAK) 1001 Project (116E097), by the Spanish project TIN2016-74946-P (MINECO/FEDER, UE) and CERCA Programme / Generalitat de Catalunya and the Estonian Centre of Excellence in IT (EXCITE) funded by the European Regional Development Fund. The authors also gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X Pascal GPU. This work is partially supported by ICREA under the ICREA Academia programme.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Litvin, A., Nasrollahi, K., Escalera, S. et al. A novel deep network architecture for reconstructing RGB facial images from thermal for face recognition. Multimed Tools Appl 78, 25259–25271 (2019). https://doi.org/10.1007/s11042-019-7667-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-7667-4