Abstract
Medical alterations on the facial region introduce skin consistency deviations amongst images of the same individual, thus making face recognition after medical alterations complicated than in regular circumstances. Cosmetic surgeries lead to medical identity thefts. Thus this makes one’s security a serious concern and human identification after medical alterations a critical dare. As prevailing techniques for human identification after surgery are not favorable, so in the present picture cosmetic therapies score above facial recognition. Neural models are not used till date to recognize surgically altered faces. The proposed approach uses a Deep Feed Forward Neural Network to recognize surgically altered faces. The innovation lies in weight update during back propagation which results into optimization of computational complexity and thus less training. While calculating error gradient during weight update, trace of inversed Hessian matrix is evaluated instead of computing the entire matrix which results into cumbersome calculations. Trace reveals vital facial features essential for recognition. Training deep models is computationally expensive but our scheme reduces computation complexity. Rank 1 Recognition Rates (RR) are obtained empirically by bootstrap sampling with 95% confidence interval level for the plastic surgery facial dataset. RR values 97.89% and 98.24% obtained for global and local surgeries are best reported till date in literature. This dataset is unbalanced so with biased metrics (RR and MSE (Mean Square Error)) unbiased metrics (F-score and R (Regression Coefficient)) are also analyzed. The recognition results obtained are equivalent to existing deep models which are computationally expensive and require large processing power.
Similar content being viewed by others
References
Aggarwal G, Biswas S, Flynn PJ, Bowyer KW (2012) A sparse representation approach to face matching across plastic surgery. IEEE Workshop on the Applications of Computer Vision (WACV), Breckenridge, CO, pp 113–119. https://doi.org/10.1109/WACV.2012.6163008
Ali A, Sagayan V, Malik A, Aziz A (2016) Proposed face recognition system after plastic surgery. IET Comput Vis 10:342–348
Alzubi J, Nayyar A, Kumar A (2018) Machine learning from theory to algorithms: an overview. J Phys Conf Ser 1142:012012. https://doi.org/10.1088/1742-6596/1142/1/012012
Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Surf: speeded up robust features. Comput Vis Image Underst 110(3):346–359
Bhatt HS, Bharadwaj S, Singh R, Vatsa M, Noore A (2011) Evolutionary granular approach for recognizing faces altered due to plastic surgery. In: Proceedings of international conference on automatic face gesture recognition and workshops, Santa Barbara, pp 720–725. https://doi.org/10.1109/FG.2011.5771337
Bhatt HS, Bharadwaj S, Singh R, Vatsa M (2013) Recognizing surgically altered face images using multiobjective evolutionary algorithm. IEEE Trans Inf Forensics Secur 8:89–100. https://doi.org/10.1109/TIFS.2012.2223684
De Marsico M, Nappi M, Riccio D, Wechsler H (2011) Robust face recognition after plastic surgery using local region analysis. In: Kamel M, Campilho A (eds) Image Analysis and Recognition. Lecture Notes in Computer Science, vol 6754. Springer, Berlin. https://doi.org/10.1007/978-3-642-21596-4_20
Eisenthal Y, Dror G, Ruppin E (2006) Facial attractiveness: beauty and the machine. Neural Comput 18:119–142
El Said SA, Abol Atta HM (2014) Geometrical face recognition after plastic surgery. Int J Comput Appl Technol 49(3/4):352–364. https://doi.org/10.1504/IJCAT.2014.062371
Grm K, Štruc V, Artiges A, Caron M, Ekenel H (2017) Strengths and weaknesses of deep learning models for face recognition against image degradations. IET Biometrics 7:81–89. https://doi.org/10.1049/iet-bmt.2017.0083
Gupta R, Khari M, Gupta D, Crespo RG (2020) Fingerprint image enhancement and reconstruction using the orientation and phase reconstruction. Inf Sci, ISSN 0020-0255 530:201–218. https://doi.org/10.1016/j.ins.2020.01.031
Ibrahim RM, Abou-Chadi FEZ, Samra AS (2013) Plastic surgery face recognition: a comparative study of performance. IJCSI 10(5) No 2
Jillela R, Ross A (2012). Mitigating effects of plastic surgery: fusing face and ocular biometrics. IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS), Arlington, pp 402–411. https://doi.org/10.1109/BTAS.2012.6374607
Kermani BG, Schiffman SS, Troy Nagle H (2005) Performance of the Levenberg–Marquardt neural network training method in electronic nose applications. Sensors Actuators B Chem 110(1):13–22, ISSN 0925-4005. https://doi.org/10.1016/j.snb.2005.01.008
Lakshmiprabha NS, Bhattacharya J, Majumder S (2011) Face recognition using multimodal biometric features. In: 2011 international conference on image information processing, pp 1–6. https://doi.org/10.1109/ICIIP.2011.6108945
Leyvand T, Cohen-Or D, Dror G, Lischinski D (2008) Data-driven enhancement of facial attractiveness. ACM Trans Graph 27(3):article 38
Li Y, Li Y, Xu K, Yan Q, Deng RH (2018) Empirical study of face authentication systems under OSNFD attacks. IEEE Trans Dependable Secure Comput 15(2):231–245. https://doi.org/10.1109/TDSC.2016.2550459
Liu X, Shan S, Chen X (2012). Face recognition after plastic surgery: a comprehensive study. In: Asian Conference on Computer Vision, pp 565–576
Liu X, Shan S, Chen X (2013) Face recognition after plastic surgery: a comprehensive study. In: Lee KM, Matsushita Y, Rehg JM, Hu Z (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture notes in computer science, vol 7725. Springer, Berlin. https://doi.org/10.1007/978-3-642-37444-9_44
Mun M, Deorankar A (2014) Implementation of plastic surgery face recognition using multimodal biometric features. Int J Comput Sci Inf Technol 5(3):3711–3715
Nappi M, Ricciardi S, Tistarelli M (2016) Deceiving faces: when plastic surgery challenges face recognition. Image Vis Comput 54:71–82, ISSN 0262-8856. https://doi.org/10.1016/j.imavis.2016.08.012
Oloyede MO, Hancke GP, Myburgh HC (2020) A review on face recognition systems: recent approaches and challenges. Multimed Tools Appl 79:27891–27922. https://doi.org/10.1007/s11042-020-09261-2
Plastic surgery face database (2020) http://iiitd.edu.in/iab/Image_Analysis_and_Biometrics_Group/Resources.html/, http://iabrubric.org/resources.html/
Ricanek K (2013) The next biometric challenge: medical alterations. IEEE Computer Society, pp 94–96
Sabharwal T, Gupta R (2019) Human identification after plastic surgery using region based score level fusion of local facial features. J Inf Secur Appl 48:102373, ISSN 2214-2126. https://doi.org/10.1016/j.jisa.2019.102373
Sabharwal T, Gupta R (2020) Facial marks for enhancing facial recognition after plastic surgery. Int J Inf Technol 13:391–396. https://doi.org/10.1007/s41870-020-00566-x
Sabharwal T, Gupta R, Son LH, Kumar R, Jha S (2019) Recognition of surgically altered face images: an empirical analysis on recent advances. Artif Intell Rev 52:1009–1040. https://doi.org/10.1007/s10462-018-9660-0
Singh R, Vatsa M, Noore A (2009) Effect of plastic surgery on face recognition: a preliminary study. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp 72–77
Singh R, Vatsa M, Bhatt HS, Bharadwaj S, Noore A, Nooreyezdan SS (2010) Plastic surgery: a new dimension to face recognition. IEEE Trans Inf Forensics Secur 5(3):441–448. https://doi.org/10.1109/TIFS.2010.2054083
Sun Y, Wang H, Tang X (2016) Hybrid deep learning for face verification. IEEE Trans Pattern Anal Mach Intell 38(10):1997–2009. https://doi.org/10.1109/TPAMI.2015.2505293
Verghis TJ, Uma S, Bhuvaneshwari P (2014) A multi-objective evolutionary approach to face matching across plastic surgery. COMPUSOFT 3(2):529–532
Wang, M., & Weihong, D. (2018). Deep face recognition: a survey.
Wilamowski BM, Yu H (2010) Improved computation for Levenberg–Marquardt training. IEEE Trans Neural Netw 21(6):930–937. https://doi.org/10.1109/TNN.2010.2045657
Xiao X, Zhou Y (2018) Two-dimensional quaternion PCA and sparse PCA. IEEE Trans Neural Netw Learn Syst:1–15
Xu Y, Fang X, Li X, Yang J, You J, Liu H, Teng S (2014) Data uncertainty in face recognition. IEEE Trans Cybern 44(10):1950–1961. https://doi.org/10.1109/TCYB.2014.2300175
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
Sabharwal, T., Gupta, R. Deep facial recognition after medical alterations. Multimed Tools Appl 81, 25675–25706 (2022). https://doi.org/10.1007/s11042-022-12895-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12895-z