PYTHON DASTURLASH TILIDA KOMPYUTER KO‘RISH TEXNOLOGIYALARI ASOSIDA INSON YUZINING ORIENTATSIYASINI (O‘NG/CHAP EGILISHINI) ANIQLASH ALGORITMINI ISHLAB CHIQISH
Keywords:
Python, kompyuter ko‘rish, yuzni aniqlash, yuz orientatsiyasi, chap/o‘ng egilish, real vaqt tizimi, yuz landmarklari, geometrik tahlil, tasvirni qayta ishlash, inson-kompyuter interfeysi, biometrik tizim, OpenCV, yuz kuzatuv tizimi, algoritm ishlab chiqish, sun’iy intellekt asoslari.Abstract
Ushbu maqolada Python dasturlash tilida kompyuter ko‘rish texnologiyalari asosida inson yuzining fazoviy orientatsiyasini, ya’ni o‘ng yoki chap tomonga egilgan holatini aniqlash algoritmini ishlab chiqish masalasi yoritilgan. Tadqiqotning asosiy maqsadi — real vaqt rejimida yuz holatini aniqlashga qodir bo‘lgan samarali va aniqligi yuqori bo‘lgan algoritmni yaratish hamda uning amaliy qo‘llanilish imkoniyatlarini o‘rganishdan iborat.
Tadqiqot jarayonida yuzni aniqlash, yuz nuqtalarini (landmark) belgilash va iometric tahlil qilish usullaridan foydalanildi. Yuzning chap va o‘ng tomonga og‘ish darajasi burun, ko‘z va lab nuqtalarining nisbiy koordinatalari asosida hisoblandi. Ushbu jarayonda kompyuter ko‘rish modellaridan foydalanish orqali tasvirlardan yuzni ajratib olish va uning yo‘nalishini aniqlash jarayoni optimallashtirildi.
Natijalar shuni ko‘rsatdiki, ishlab chiqilgan algoritm real vaqt rejimida yuz orientatsiyasini yuqori aniqlik bilan aniqlay oladi. Shuningdek, turli yorug‘lik sharoitlari va yuz holatlarida ham barqaror ishlash imkoniyatiga ega ekanligi aniqlandi. Ushbu yondashuv video kuzatuv tizimlari, inson-kompyuter interfeysi, xavfsizlik tizimlari va iometric identifikatsiya sohalarida qo‘llanilishi mumkin.
References
Tereza F., Murphy K. Face Alignment and Pose Estimation in Computer Vision Systems. – IEEE CVPR Workshops, 2021.
Zhang K., Zhang Z., Li Z. Real-Time Face Detection and Alignment Using Deep Learning. – Journal of Visual Communication and Image Representation, 2019.
Baltrusaitis T., Robinson P., Morency L. OpenFace: An Open Source Facial Behavior Analysis Toolkit. – IEEE Winter Conference on Applications of Computer Vision, 2016.
OpenCV Documentation Team. Real-Time Face Processing Modules. OpenCV.org, 2025.
Kazemi V., Sullivan J. One Millisecond Face Alignment with an Ensemble of Regression Trees. – CVPR, 2014.
Bulat A., Tzimiropoulos G. How Far are We from Solving the 2D & 3D Face Alignment Problem?. – International Journal of Computer Vision, 2017.
Deng J., Zhou Y., Zafeiriou S. RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild. – CVPR, 2020.
Shan S., Gao W., Cao B. Driver Fatigue Detection Based on Facial Orientation and Eye Tracking. – Pattern Recognition Letters, 2018.
Li S., Deng W. Deep Facial Landmark Detection: A Survey. – IEEE Transactions on Pattern Analysis, 2022.
Huang G., Mattar M., Berg T. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. – University of Massachusetts, 2007.
