Yasmien, Syahwa Lila (2026) IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK UNTUK DETEKSI EMOSI WAJAH PADA ANAK SEKOLAH LUAR BIASA (SLB) DI KOTA MADIUN. S1 thesis, Universitas PGRI Madiun.
![[img]](https://eprint.unipma.ac.id/style/images/fileicons/text.png) |
Text
Halaman Depan sampai Daftar Lampiran.pdf Download (513kB) |
|
Text
ABSTRAK_Skripsi.pdf Download (91kB) |
|
Text
c_BAB_I.pdf Download (189kB) |
|
Text
d_BAB_II.pdf Download (333kB) |
|
Text
e_BAB_III.pdf Restricted to Repository staff only Download (525kB) |
|
Text
BAB IV_Skripsi.pdf Restricted to Repository staff only Download (2MB) |
|
Text
BAB V_Skripsi.pdf Download (20kB) |
|
Text
Daftar Pustaka_Skripsi.pdf Download (248kB) |
|
Text
Lampiran_Skripsi.pdf Restricted to Repository staff only Download (550kB) |
Abstract
This study was motivated by the need for learning media that can help students at special schools recognize emotions through facial expressions. It aims to develop a facial emotion detection system based on a Convolutional Neural Network (CNN) as an educational tool for special-school students in Madiun City, Indonesia. The study combines quantitative and qualitative approaches through observation, interviews, dataset processing, model development, system testing, and user evaluation. The dataset combines the public FER2013 dataset with facial images collected from special-school students. The images undergo preprocessing, including resizing, normalization, augmentation, and splitting into training and testing sets. The CNN model is then integrated into a Streamlit-based web application that captures facial images through a camera and displays the predicted emotion category along with simple educational recommendations. Functional testing is conducted using the Black Box Testing method, while user evaluation involves students and teachers. The results show that the application was successfully developed and its main features operate according to the defined functional requirements. The CNN model can classify facial expressions into the emotion categories learned during training, while teacher feedback indicates that the application has potential as a supporting tool for emotion-recognition learning. The detection output remains an estimate and should be considered alongside teachers’ direct observations; it is not intended for psychological diagnosis. Keywords: Convolutional Neural Network, facial emotion detection, special school, Streamlit, educational tool
| Item Type: | Thesis/Skripsi/Tugas Akhir (S1) |
|---|---|
| Kata Kunci: | Kata kunci: Convolutional Neural Network, deteksi emosi wajah, SLB, Streamlit, media edukasi Keywords: Convolutional Neural Network, facial emotion detection, special school, Streamlit, educational tool |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Teknik > Sistem Informasi |
| Depositing User: | YASMIEN LILA SYAHWA |
| Date Deposited: | 26 Oct 2026 03:03 |
| Last Modified: | 26 Oct 2026 03:03 |
| URI: | http://eprint.unipma.ac.id/id/eprint/10419 |
Actions (login required)
 |
View Item |
