Facial Recognition and Emotion Classification Using CNN

Ramachandran Nair, Devika (2024) Facial Recognition and Emotion Classification Using CNN. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (360kB) | Preview
Preview	PDF (Configuration Manual) Download (180kB) | Preview

Abstract

The matter of recognizing the emotions’ facets by analyzing facial expressions represented short FER has gained importance in recent years. It has a realization in such areas as mental health tracking, using it for HCI and analyzing customers in their shopping activities. The deployed face recognition mechanisms have shown high accuracy at classifying images the human emotion includes six basic emotions which are happiness, sadness, anger, fear, disgust, and surprise. The ANN of the Convolutional type guided the entire model development process. On the CNNs approach out model would expect to guidance markers such as smile, anger etc. The key feature of the proposed technology is the automated workflow as it eliminates spotting internal and external objects. A blocker for human-emotion recognition mechanisms was set at 70% and above, with the automated Human Assistance Technology System surpassed it by approximately 22%. This loss is Frequently reported to be higher in practical settings as an outcome of having to deal with multiple classes of subordinate tasks or simply more complex systems in real human settings. Hence, we consider the ratio of images and books wheel models and hence were able to get the desired effect. In addition, basic measures of human contact experience in promo activities including temporality and diplopia were put into consideration. Even with a GPU their mean average time conferred on average was about 102ms. Nevertheless, additional information should be paid to control the convex feature to measure bilateral scanner mechanism that could recognize extra layers on multiple folds or resolution levels. Indicating that with better patches in their system HATs solution are said to be able to recognize human emotion in real world settings modelled after GANs. From this paper, we have sought to develop a practical FER mechanism. Thus, it can indeed make conclusions based on detecting human emotions in different real life objects relations.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Khan, Sallar UNSPECIFIED
Uncontrolled Keywords:	Facial Emotion Recognition; Convolutional Neural Networks; Feature Extraction; Emotion Classification; Data Augmentation; Human-Computer Interaction; Real-Time Applications; Deep Learning
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision B Philosophy. Psychology. Religion > Psychology > Emotions
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 11:17
Last Modified:	04 Sep 2025 11:17
URI:	https://norma.ncirl.ie/id/eprint/8783

Actions (login required)

View Item