Abstract

Face recognition has been a prominent research topic in the field of security. The increasing demand for secure organizational environments and advancements in artificial intelligence has further emphasized the importance of human face recognition. Over time, researchers have explored face recognition methods to accurately identify complete facial images. However, real-world scenarios often involve challenges such as occlusions and noise, which significantly impact recognition accuracy. To address these issues, further development is necessary to enhance performance when dealing with obscured and noisy images. This study presents a simple and efficient deep learning (DL)-based facial recognition method capable of recognizing both occluded and distorted faces. A novel approach, termed robust facial recognition in biometric authentication using the modified whale optimization algorithm (RFRB-MWOA), was introduced. RFRB-MWOA leverages artificial intelligence and advanced DL models to recognize various emotional states effectively. The method employs histogram equalization to standardize brightness and hue levels across different individuals and expressions, ensuring consistent image quality. The process incorporates the mask_convolutional neural network (mask_CNN) model, which uses the modified whale optimization algorithm (MWOA) for hyperparameter tuning. Mask_CNN utilizes probabilistic max-pooling to preserve distinctive features while maintaining feature variability, improving the robustness of the model. Additionally, a layered activation function is applied to produce flexible, normalized information for better generalization. Experimental results demonstrate that the proposed approach outperforms state-of-the-art methods and effectively addresses recognition precision issues caused by input mismatches, showcasing its potential for reliable biometric authentication.

Keyword

Face recognition, Biometric authentication, Deep learning, Mask_convolutional neural network, Whale optimization algorithm.

Cite this article

Leelavathi M, Kannan D.Robust facial recognition using deep learning and modified whale optimization algorithm for biometric authentication. International Journal of Advanced Technology and Engineering Exploration. 2024;11(121):1681-1698. DOI:10.19101/IJATEE.2023.10102317

Refference

[1]Sezer OB, Dogdu E, Ozbayoglu AM. Context-aware computing, learning, and big data in internet of things: a survey. IEEE Internet of Things Journal. 2017; 5(1):1-27.

[2]De KA, Bart Y, Gu X, Liu SQ, Robinson SG, Kannan PK. Opportunities and challenges of using biometrics for business: developing a research agenda. Journal of Business Research. 2021; 136:52-62.

[3]Alwan HB, Ku-mahamud KR. Cancellable face template algorithm based on speeded-up robust features and winner-takes-all. Multimedia Tools and Applications. 2020; 79(39):28675-93.

[4]Cui K. Interacting with ubiquitous IoT devices via RF sensing. Doctorate Dissertation, Hong Kong Polytechnic University. 2023.

[5]Carlaw S. Impact on biometrics of Covid-19. Biometric Technology Today. 2020; 2020(4):8-9.

[6]Salau AO, Jain S. Feature extraction: a survey of the types, techniques, applications. In international conference on signal processing and communication 2019 (pp. 158-64). IEEE.

[7]Singh G, Chhabra I. Effective and fast face recognition system using complementary OC-LBP and HOG feature descriptors with SVM classifier. Journal of Information Technology Research. 2018; 11(1):91-110.

[8]Shi Q, Li H, Shen C. Rapid face recognition using hashing. In computer society conference on computer vision and pattern recognition 2010 (pp. 2753-60). IEEE.

[9]Seetharaman K. Image retrieval based on micro-level spatial structure features and content analysis using full range gaussian Markov random field model. Engineering Applications of Artificial Intelligence. 2015; 40:103-16.

[10]Hatamikia S, Maghooli K, Nasrabadi AM. The emotion recognition system based on autoregressive model and sequential forward feature selection of electroencephalogram signals. Journal of Medical Signals & Sensors. 2014; 4(3):194-201.

[11]He R, Tan T, Davis L, Sun Z. Learning structured ordinal measures for video-based face recognition. Pattern Recognition. 2018; 75:4-14.

[12]Pujol FA, Pujol M, Jimeno-morenilla A, Pujol MJ. Face detection based on skin color segmentation using fuzzy entropy. Entropy. 2017; 19(1):1-22.

[13]Das A, Dantcheva A, Bremond F. Mitigating bias in gender, age and ethnicity classification: a multi-task convolution neural network approach. In proceedings of the European conference on computer vision workshops 2018 (pp. 573-85). ACM.

[14]Zhang F, Yu Y, Mao Q, Gou J, Zhan Y. Pose-robust feature learning for facial expression recognition. Frontiers of Computer Science. 2016; 10:832-44.

[15]Zafeiriou S, Zhang C, Zhang Z. A survey on face detection in the wild: past, present and future. Computer Vision and Image Understanding. 2015; 138:1-24.

[16]Tu H, Li K, Zhao Q. Robust face recognition with assistance of pose and expression normalized albedo images. In proceedings of the 5th international conference on computing and artificial intelligence 2019 (pp. 93-9). ACM.

[17]Chen X, Lan X, Liang G, Liu J, Zheng N. Pose-and-illumination-invariant face representation via a triplet-loss trained deep reconstruction model. Multimedia Tools and Applications. 2017; 76:22043-58.

[18]Ding C, Xu C, Tao D. Multi-task pose-invariant face recognition. IEEE Transactions on image Processing. 2015; 24(3):980-93.

[19]Luque J, Cortes G, Segura C, Maravilla A, Esteban J, Fabregat J. End-to-end photopleth YsmographY (PPG) based biometric authentication by using convolutional neural networks. In 26th European signal processing conference 2018 (pp. 538-42). IEEE.

[20]Donuk K, Arı A, Özdemir MF, Hanbay D. Deep feature selection for facial emotion recognition based on BPSO and SVM. Journal of Polytechnic. 2023; 26(1):131-42.

[21]Lokku G, Reddy GH, Prasad MG. OPFaceNet: optimized face recognition network for noise and occlusion affected face images using hyperparameters tuned convolutional neural network. Applied Soft Computing. 2022; 117:108365.

[22]Sahan JM, Abbas EI, Abood ZM. A facial recognition using a combination of a novel one dimension deep CNN and LDA. Materials Today: Proceedings. 2023; 80:3594-9.

[23]Febrian R, Halim BM, Christina M, Ramdhan D, Chowanda A. Facial expression recognition using bidirectional LSTM-CNN. Procedia Computer Science. 2023; 216(2022):39-47.

[24]Hu Z, Tereykovskiy I, Zorin Y, Tereykovska L, Zhibek A. Optimization of convolutional neural network structure for biometric authentication by face geometry. In advances in computer science for engineering and education 2019 (pp. 567-77). Springer International Publishing.

[25]Page A, Kulkarni A, Mohsenin T. Utilizing deep neural nets for an embedded ECG-based biometric authentication system. In biomedical circuits and systems conference 2015 (pp. 1-4). IEEE.

[26]Benradi H, Chater A, Lasfar A. A hybrid approach for face recognition using a convolutional neural network combined with feature extraction techniques. IAES International Journal of Artificial Intelligence. 2023; 12(2):627-40.

[27]Anwarul S, Choudhury T, Dahiya S. A novel hybrid ensemble convolutional neural network for face recognition by optimizing hyperparameters. Nonlinear Engineering. 2023; 12(1):20220290.

[28]Revathy G, Raj KB, Kumar A, Adibatti S, Dahiya P, Latha TM. Investigation of E-voting system using face recognition using convolutional neural network (CNN). Theoretical Computer Science. 2022; 925:61-7.

[29]Wen Y, Zhang K, Li Z, Qiao Y. A discriminative feature learning approach for deep face recognition. In computer vision–ECCV: 14th European conference, Amsterdam, the Netherlands 2016 (pp. 499-515). Springer International Publishing.

[30]Abd EM, Mirjalili S. A hyper-heuristic for improving the initial population of whale optimization algorithm. Knowledge-Based Systems. 2019; 172:42-63.

[31]Rahnamayan S, Tizhoosh HR, Salama MM. Quasi-oppositional differential evolution. In congress on evolutionary computation 2007 (pp. 2229-36). IEEE.

[32]http://shuoyang1213.me/WIDERFACE/. Accessed 20 August 2024.

[33]Jain V, Learned-miller E. FDDB: a benchmark for face detection in unconstrained settings. UMass Amherst Technical Report; 2010:1-11.

[34]Sonon SJ, Djara T, Bello AW, Ousmane M. Securing the user registration process in an IP telephony system using blockchain and KYC technologies. Journal of Scientific and Engineering Research. 2024; 11(1):238-47.

[35]Vadim S, Firdaus M, Rhee KH. Privacy-preserving decentralized biometric identity verification in car-sharing system. Journal of Multimedia Information System. 2024; 11(1):17-34.

[36]Guleria A, Krishan K, Sharma V, Kanchan T. Global adoption of facial recognition technology with special reference to India-present status and future recommendations. Medicine, Science and the Law. 2024; 64(3): 236-244.