RASYID, GUILLIANO (2025) REAL-TIME FACIAL EMOTION RECOGNITION SYSTEM USING YOU ONLY LOOK ONCE (YOLO) VERSION 8. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411285_Guilliano Rasyid_Abstrak.pdf Download (11kB) |
Abstract
Real-time facial emotion recognition plays a vital role in developing interactive technologies such as human-computer interaction and intelligent systems. Despite significant advancements, challenges remain in achieving high accuracy and speed due to variations in lighting, facial poses, and subtle expressions. This study implements the You Only Look Once (YOLO) version 8 algorithm, known for its fast and accurate object detection capabilities. The model was trained using a preprocessed and categorized facial emotion image dataset and tested through a web-based prototype with an intuitive interface. The system detects faces from live webcam video streams and classifies emotions in real-time. Testing results demonstrate that the system can classify eight facial emotion categories: anger, content, disgust, fear, happiness, neutral, sadness, and surprise. The highest classification accuracies were achieved in happiness, neutral, and sadness categories, each reaching 96%, while the content category achieved 84% accuracy. The system displays emotion labels and bounding boxes on detected faces in real-time. This prototype holds significant potential for broader applications and can be further developed to meet various user needs. Keywords: Recognition, Emotion, Face, YOLOv8.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 16 Jul 2025 09:08 |
| Last Modified: | 16 Jul 2025 09:08 |
| URI: | http://eprints.uty.ac.id/id/eprint/18185 |
Actions (login required)
 |
View Item |
