Niqobli inson yuzini tanib olish texnologiyalaridagi yutuqlar bo‘yicha keng qamrovli sharh
Kalit so'zlar:
Konvolyutsiya neyron tarmoqlari, COVID-19, Chuqur o‘rganish, Yuzni aniqlash, Siyam neyron tarmoqlariAnnotatsiya
COVID-19 pandemiyasi davrida niqoblarning keng tarqalishi yuzni aniqlash tizimlariga yangi qiyinchiliklar keltirib chiqardi. Ushbu tadqiqot chuqur o‘rganish texnikalari, xususan, konvolyutsion neyron tarmoqlari (CNN) va egizak tarmoqlar yordamida niqobli yuzni aniqlash sohasidagi so‘nggi yutuqlarni ko‘rib chiqadi. Maqolada yorug‘lik o‘zgarishi, yuzning turli pozitsiyalari va qisman yashirish kabi asosiy muammolar tahlil qilinadi. Sun'iy ma'lumotlar bazalari va multimedia usullaridan foydalanib, tizimlarning aniqligini oshirish yo‘llari muhokama qilinadi. Xavfsizlik va tibbiyot sohalarida niqobli yuzni aniqlashning amaliy qo‘llanilishi va kelajakdagi tadqiqot yo‘nalishlari ko‘rsatilgan. Tadqiqot real sharoitda tanib olish tizimlarining samaradorligini oshirish uchun yangi algoritmlar ishlab chiqish zarurligi ta‘kidlanadi.
Библиографические ссылки
1.V. Chakkaravarthy va boshq., Deep learning–based face mask detection for COVID-19, 6th International Conference on Communication & Electronics Systems (ICCES), 2021.
2.S. Fujieda, K. Takayama, T. Hachisuka, Face recognition using mask component, IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021, pp. 1503–1512.
3.M. Hariri, Face Mask Recognition using Machine Learning, International Journal of Advanced Computer Science and Applications, 2021.
4.S. Sony va boshq., Real-time helmet and mask detection using deep learning, International Research Journal of Engineering and Technology, 2020.
5.K. Zhang va boshq., Face completion using GAN for masked face recognition, IEEE Access, 2020.
6.A. Alzu’bi va boshq., A comprehensive survey on masked face recognition: challenges, methods, and future directions, ACM Computing Surveys, 2023.
7.F. Schroff, D. Kalenichenko, J. Philbin, FaceNet: A unified embedding for face recognition and clustering, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
8.Y. Sun va boshq., Deep learning face representation by joint identification–verification, NeurIPS, 2014.
9.A. Krizhevsky, I. Sutskever, G. Hinton, ImageNet classification with deep convolutional neural networks, NeurIPS, 2012. (AlexNet)
10.K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv, 2014. (VGG16, VGG19)
11.K. He va boshq., Deep residual learning for image recognition, IEEE CVPR, 2016. (ResNet)
12.A. Howard va boshq., MobileNets: Efficient CNNs for mobile vision applications, arXiv, 2017.
13.F. Chollet, Xception: Deep learning with depthwise separable convolutions, IEEE CVPR, 2017.
14.W. Liu va boshq., SphereFace: Deep hypersphere embedding for face recognition, IEEE CVPR, 2017.
15.J. Deng va boshq., ArcFace: Additive angular margin loss for deep face recognition, IEEE CVPR, 2019.
16.J. Goodfellow va boshq., Generative Adversarial Nets, NeurIPS, 2014. (GAN)
17.T. Koch va boshq., Siamese neural networks for one-shot image recognition, ICML Workshop, 2015. (SNN)
