Emotion Recognition using a Multi-view learning method

Abstract

The increasing use of computing devices and applications in human daily life triggers the need for natural human-computer interaction. Emotion Recognition using multiple features using a semi-serial fusion method is proposed. The study analyses the impact of the feature combinations in the enhancement of the recognition enhancement. The paper presents the use of the multi-view learning principle to a fusion of different features for one emotion expression-based recognition. The results prove that a planned method is operative. The proposed combination method outperforms the use of one type of features and the concatenated way in recognition accuracy, improvement of execution time, and stability.

Chuqur o‘rganishga asoslangan yuz tahlili: xususiyatlarni ajratib olish va his-tuyg‘ularni tushunish

“…Yuz xususiyatlari nuqtalari -bu yuz tasvirlaridagi ko'rinadigan belgilar yoki tasvirlarning qiziqarli qismini tashkil etuvchi nuqtalar, masalan, ko'z markazlari, burun uchi, og'iz burchaklari va boshqa ko'zga ko'ringan yuz nuqtalari. Ular ko'pincha mos yozuvlar yoki o'lchash uchun ishlatiladi, 6-rasmda faol ko'rinish metodlari moslashuvi va tegishli animatsiya parametrlari asosida olingan yuz xususiyatlari nuqtalari misoli keltirilgan [18].…”

“…Yuz harakati birligi tadqiqoti yuz mushaklari harakatini o'rganadi va yuz harakati o'zgarishlarini tavsiflaydi. Ekman Paul va Friesen ishlariga asoslanib, Facial Action Coding System (FACS) o'lchov texnologiyasida yuz ifodasini qo'llashning eng samarali usullaridan biri sifatida qarash mumkin [18]. Harakat birliklari orqali yuz ifodalarini aniq ajratib olishlari mumkin, ammo ular aniq joylashuvi tufayli yuz ifodasini aniqlashda kamroq qo'llaniladi , 7-rasmda harakat birliklarining ayrim misollari keltirilgan.…”

Construction of self-learning classroom history teaching mode based on human-computer interaction emotion recognition

“…Since the current facial recognition features are not well-defined, Kommineni et al ( 2021 ) proposed a method that can improve high performance computing in terms of facial expression recognition accuracy. Because the increasing use of computing devices and applications in human daily life has triggered the need for natural human-computer interaction, Mukeshimana et al ( 2020 ) proposed emotion recognition using multiple features using a semi-serial fusion method. Since speech emotion recognition has become the core of most human-computer interaction applications in the modern world, Zvarevashe and Olugbara ( 2020 ) developed a custom 2D convolutional neural network that can perform feature extraction and classification of sounds.…”