To address the issues of insufficient accuracy and significant impact of image noise on model performance in current facial recognition systems, this study proposes a new framework that integrates wavelet transform, an improved multi-task cascaded convolutional neural network (MTCNN), and genetic algorithms (GA). This framework utilizes wavelet transform for image denoising; optimizes MTCNN by introducing a hybrid threshold function and a confidence candidate box retention mechanism to effectively address information loss issues; and applies GA for feature compensation and optimization. Experimental results demonstrate that this method significantly improves the accuracy, recall rate, regression value, and model stability of facial recognition, effectively enhancing the system’s robustness under noise interference, and provides an effective solution for optimizing facial recognition performance.
LiWLiJCaoD, et al.Neural mechanism of noise affecting face recognition. Neuroscience2021; 468(3): 211–219.
2.
MadarkarJSharmaPSinghRP. Sparse representation for face recognition: a review paper. IET Image Process2021; 15(9): 1825–1844.
3.
ZamanFHK. Locally lateral manifolds of normalised Gabor features for face recognition. IET Comput Vis2020; 14(4): 122–130.
4.
KarANeogiPPG. Triangular coil pattern of local radius of gyration face for heterogeneous face recognition. Appl Intell2020; 50(3): 698–716.
5.
RathnayakeNRathnayakeUDangTL, et al.An efficient automatic fruit-360 image identification and recognition using a novel modified cascaded-ANFIS algorithm. Sensors2022; 22(12): 4401–4402.
6.
ShakraniKVKanyangararaNMParowaPT, et al.A deep learning model for face recognition in presence of mask. Acta Inform Malays2022; 6(2): 38–41.
7.
WangZ-YAbhadiomhenSELiuZ-F, et al.Multi-view intrinsic low-rank representation for robust face recognition and clustering. IET Image Process2021; 15(14): 3573–3584.
8.
ChenTGaoTLiS, et al.A novel face recognition method based on fusion of LBP and HOG. IET Image Process2021; 15(14): 3559–3572.
9.
McguginRWNewtonATTamber-RosenauB, et al.Thickness of deep layers in the fusiform face area predicts face recognition. J Cognit Neurosci2020; 32(7): 1316–1329.
10.
XueSRenHP. Single sample per person face recognition algorithm based on the robust prototype dictionary and robust variation dictionary construction. IET Image Process2022; 16(3): 742–754.
11.
HeMZhangJShanS, et al.Locality-aware channel-wise dropout for occluded face recognition. IEEE Trans Image Process2022; 31(5): 788–798.
12.
LiuYChenJ. Multi-factor joint normalisation for face recognition in the wild. IET Comput Vis2021; 15(6): 405–417.
13.
XiaoqianYGoffauxVBrunoR. Coarse-to-Fine(r)Automatic familiar face recognition in the human brain. Cerebr Cortex2021; 32(8): 1560–1573.
14.
HaoMLiuGXieD. Hyperspectral face recognition with a spatial information fusion for local dynamic texture patterns and collaborative representation classifier. IET Image Process2021; 15(8): 1617–1618.
15.
ChoiJYLeeB. Ensemble of deep convolutional neural networks with gabor face representations for face recognition. IEEE Trans Image Process2020; 29(3): 3270–3281.
16.
GundogduBBiancoM. Collaborative similarity metric learning for face recognition in the wild. IET Image Process2020; 14(9): 1759–1768.
17.
SadeghzadehAEbrahimnezhadH. Pose-invariant face recognition based on matching the occlusion free regions aligned by 3D generic model. IET Comput Vis2020; 14(5): 268–277.
18.
KocMErginSGulmezogluMB, et al.Use of gradient and normal vectors for face recognition. IET Image Process2020; 14(10): 2121–2129.
19.
YanXRossionB. A robust neural familiar face recognition response in a dynamic (periodic) stream of unfamiliar faces. Cortex2020; 132(10): 281–295.
20.
LiuQJiangBZhangJL, et al.Semi-supervised uncorrelated dictionary learning for color face recognition. IET Comput Vis2020; 14(3): 92–100.
21.
MishraNKKumarSSinghSK. MmLwThV framework: a masked face periocular recognition system using thermo-visible fusion. Appl Intell2022; 53(3): 2471–2487.
22.
HebbiCMamathaH. Comprehensive dataset building and recognition of isolated handwritten Kannada characters using machine learning models. Artif Intell Appl2023; 1(3): 179–190.
23.
AdamsSOAzikweEZubairMA. Artificial neural network analysis of some selected KDD CUP99 dataset for intrusion detection. Acta inform Malays2022; 6(2): 55–61.
HidayatFElvianiUSitumorangGB, et al.Face recognition for automatic border control: a systematic literature review. IEEE Access2024; 12(1): 37288–37309.
26.
MelziPTolosanaRVera-RodriguezR, et al.FRCSyn-onGoing: benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems. Inf Fusion2024; 107(6): 102322–102323.
27.
OpanasenkoVMFazilovSKMirzaevON, et al.An ensemble approach to face recognition in access control systems. J Mob Multimed2024; 20(3): 749–768.
28.
SrivastavaGBagS. Modern-day marketing concepts based on face recognition and neuro-marketing: a review and future research directions. Benchmark Int J2024; 31(2): 410–438.
29.
GeorgeAEcabertCShahrezaHO, et al.Edgeface: efficient face recognition model for edge devices. IEEE Trans Biom Behav Identity Sci2024; 6(2): 158–168.
30.
SerengilSÖzpınarA. A benchmark of facial recognition pipelines and co-usability performances of modules. Bilişim Teknolojileri Dergisi2024; 17(2): 95–107.
