AVVALDAN O‘QITILGAN ILG‘OR KONVOLYUTSION NEYRON  TARMOQLARI HAMDA YAXSHILANGAN FER-2013 MA’LUMOTLAR  TO‘PLAMI YORDAMIDA YUZ HISSIYOTLARINI ANIQLASH

Admin bo'lib kirish (www.admin.slib.uz)

Tizim sinov (TEST) rejimida ishlamoqda! Murojat uchun @slib_support

Eski talqinga o'tish link

2 июн 2025

Asosiy til:O'zbek

AVVALDAN O‘QITILGAN ILG‘OR KONVOLYUTSION NEYRON TARMOQLARI HAMDA YAXSHILANGAN FER-2013 MA’LUMOTLAR TO‘PLAMI YORDAMIDA YUZ HISSIYOTLARINI ANIQLASH

Fan yo'nalishi:

683d9aa07126a.pdf

PDF

ILM-FAN VA INNOVATSION RIVOJLANISH

Maqola chop etish see more

MAQOLA ANNOTATSIYASI

Insonning yuz tasviridan hissiyotlarni aniqlash inson-kompyuterning o‘zaro ta’siri, xavfsizlik tizimlari, ruhiy salomatlik monitoringi va aqlli tizimlar uchun muhim yo‘nalishlardan biri hisoblanadi. Ayniqsa, inson-kompyuterning o‘zaro ta’siri yo‘nalishida humanoid robotlar ishlab chiqishda robotning hissiyotlarni anglab, unga mos tarzda muloqot qilishi muhim ahamiyat kasb etadi. Shu bois hissiyotlarni aniqlash tizimlarini yaratish kompyuter ko‘rish va chuqur o‘rganishning muhim masalalaridan biridir. Ushbu tadqiqotda inson yuz tasviridan hissiyotlarni aniqlash uchun avvaldan o‘qitilgan mashhur konvolyutsion neyron tarmoqlarini yaxshilangan FER-2013 ma’lumotlar to‘plamida o‘qitish orqali samarali yondashuv taklif etildi. Tadqiqot davomida ilg‘or konvolyutsion neyron tarmoqlari yordamida hissiy holatni aniqlash vazifasi samaradorligi o‘rganilib, oldindan o‘qitilgan mashhur arxitekturalar – ResNet-50, VGGNet-16, DenseNet-121 va EfficientNet-B0 modellarining yuz ifodalarini aniqlash bo‘yicha natijalari tahlil qilindi. Tadqiqotda FER-2013 ma’lumotlar to‘plamining yaxshilangan va to‘ldirilgan versiyasidan foydalanildi. Ma’lumotlarni qayta ishlash jarayonida yuz ifodalari orasidagi muvozanat buzilishi, sifati past rasmlar va noto‘g‘ri belgilangan (labeling) tasvirlar aniqlanib, ularni tuzatish ishlari amalga oshirildi. Shuningdek, overfitting muammosini kamaytirish maqsadida ma’lumotlarni kengaytirish (data augmentation) texnikalari qo‘llandi. Model natijalari aniqlik (accuracy) va yo‘qotish funksiyasi (loss) kabi mezonlar asosida baholandi.

MUALIFLAR

Teglar

# модель# model# Машинное обучение# Machine Learning# deep learning# глубокое обучение# mashinaviy o‘qitish# chuqur o‘rganish# OpenCV# CNN# FER-2013# CNN arxitekturasi# архитектура CNN# CNN architecture

Maqolani baholang

0

0 ta

Maqola idintifikatorlari

ROI:

https://eroi.uz/11.0094/A0625-0013

DOI:

Mavjud emas

Foydalanilgan adabiyotlar

Agung, E. R. (2024). Image-based facial emotion recognition using convolutional neural network on Emognition dataset. Sci Rep, 14.

Chouhayebi, H., & M. M. (2024). Human emotion recognition based on spatio-temporal facial features using HOG-HOF and VGG-LSTM. Computers, 101

Dada, E. G. (2023). Facial emotion recognition and classification using the Convolutional Neural Network-10 (CNN-10). Applied Computational Intelligence and Soft Computing, 2457898.

Ekman, P. (1978). Facial action coding systems. Consulting Psychologists Press.

Gursesli, M. (2024). Facial emotion recognition (FER) through custom lightweight CNN model: Performance evaluation in public datasets. IEEE Access, 1-1.

He, K., & X. Z. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). Las Vegas, NV, USA. https://doi. org/10.1109/CVPR.2016.90

Simonyan, K. (2015). Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556. arXiv preprint arXiv:1409.1556.

Khaireddin, Y. (2021). Facial emotion recognition: State of the art performance on FER2013. https://doi.org/10.48550/arXiv.2105.03588

Kurbanov, A. A. (2024a). Inson tanasi harakatlarini tahlil qilishda zamonaviy modellar va algoritmlarni qo‘llashni o‘rganish [Studying the application of modern models and algorithms in analyzing human body movements]. (In Uzbek). The Descendants of Al-Farghani, 169–175.

Kurbanov, A. A. (2024b). Inson yuz tasviridan hissiyotlarni aniqlash uchun geometriya xususiyatlarini va tashqi ko‘rinishga asoslangan xususiyatlarini ajratib olish [Extraction of geometric features and appearance-based features for emotion detection from human facial images]. (In Uzbek). The Descendants of Al-Farghani, 61–67.

Mao, A. M. (2023). Cross-entropy loss functions: Theoretical analysis and applications. In International Conference on Machine Learning (pp. 23803-23828).

Minaee, S. (2021). Deep-emotion: Facial expression recognition using attentional convolutional network. Sensors, 30–46.

Oguine, O. C. (2022). Hybrid facial expression recognition (2013) model for real-time emotion classification and prediction. arXiv preprint arXiv:2206.09509.

Picard, R. W. (2000). Affective computing. Massachusetts Institute of Technology.

Tan, M. (2020). Ef�icientNet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (pp. 6105–6114). PMLR.