Priyogi, Gigih (2024) SISTEM DETEKSI EKSPRESI WAJAH DENGAN METODE DEEP LEARNING MENGGUNAKAN PYTHON. S1 thesis, UNIVERSITAS SULTAN AGENG TIRTAYASA.
![[img]](https://eprints.untirta.ac.id/style/images/fileicons/text.png) |
Text (SKRIPSI)
Gigih Priyogi_2283190020_Fulltext.pdf Restricted to Registered users only Download (1MB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_02.pdf Restricted to Registered users only Download (3MB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_03.pdf Restricted to Registered users only Download (408kB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_04.pdf Restricted to Registered users only Download (27MB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_05.pdf Restricted to Registered users only Download (65kB) |
|
Text (SKRIPSI)
Gigih Priyogi_228319020_Ref.pdf Restricted to Registered users only Download (140kB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_Lamp.pdf Restricted to Registered users only Download (415kB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_CP.pdf Restricted to Registered users only Download (15MB) |
|
Text (SKRIPSI)
Gigih Priyogi_2283190020_01.pdf Restricted to Registered users only Download (2MB) |
Abstract
In the past few decades, we have witnessed the rapid growth of technology, which has changed almost every aspect of human life. Entering the era of Industrial Revolution 4.0 and the current era of Society 5.0, requires education to improve and evolve so that it can form strong Human Resources with character and ready to face the times. This research aims to produce a software that can provide information about students' emotional responses in learning and other activities on campus so that later there will be curriculum development and a more effective learning atmosphere at the Faculty of Teacher Training and Education, Sultan Ageng Tirtayasa University. This system uses the waterfall method so that it is carried out sequentially from preparation to analysis of the results of facial expression data, so that it is expected to have sufficient preparation and obtain high accuracy results. This facial expression detection system uses deep learning that can recognize 7 human facial expressions, namely angry, happy, disgusted, afraid, surprised, sad, and neutral. The system is built using python programming language and utilizes Convolutional Neural Network (CNN) as its deep learning model. The test results show that the system is able to achieve a good precision of 66.15% for angry, happy, and surprised expressions. Overall, the system achieved an accuracy of 75%, indicating a fairly good performance although there are still limitations especially on some specific expressions.
| Item Type: | Thesis (S1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
|||||||||
| Additional Information: | Dalam beberapa dekade terakhir, kita telah menyaksikan pertumbuhan teknologi yang luar biasa cepat, yang telah mengubah hampir setiap aspek kehidupan manusia. Memasuki era Revolusi Industri 4.0 dan era Society 5.0 saat ini, menuntut pendidikan untuk berbenah dan berevolusi sehingga dapat membentuk Sumber Daya Manusia yang tangguh berkarakter dan siap menghadapi perkembangan zaman. Penelitian ini bertujuan untuk menghasilkan sebuah software yang dapat memberikan informasi mengenai respon emosional mahasiswa dalam pembelajaran dan aktivitas lain di kampus sehingga nantinya terdapat pengembangan kurikulum dan suasana belajar yang lebih efektif di Fakultas Keguruan dan Ilmu Pendidikan Universitas Sultan Ageng Tirtayasa. Pembuatan Sistem ini menggunakan metode waterfall sehingga dilakukan secara berurutan mulai dari persiapan sampai dengan analisis hasil data ekspresi wajah yang, sehingga di harapkan mempunyai persiapan yang cukup matang dan memperoleh hasil akurasi yang tinggi. Sistem deteksi ekspresi wajah ini menggunakan deep learning yang dapat mengenali 7 ekspresi wajah manusia, yaitu marah, bahagia, jijik, takut, terkejut, sedih, dan netral. Sistem ini dibangun menggunakan bahasa pemrograman python dan memanfaatkan Convolutional Neural Network (CNN) sebagai model deep learning-nya. Hasil pengujian menunjukkan bahwa sistem ini mampu mencapai presisi yang baik sebesar 66,15% untuk ekspresi marah, bahagia, dan terkejut. Secara keseluruhan, sistem ini mencapai akurasi 75%, mengindikasikan kinerja yang cukup baik meskipun masih terdapat keterbatasan khususnya pada beberapa ekspresi tertentu. | |||||||||
| Uncontrolled Keywords: | Deep Learning, Facial Expression, Python, Waterfall Deep Learning, Ekspresi Wajah, Python, Waterfall | |||||||||
| Subjects: | L Education > L Education (General) T Technology > T Technology (General) |
|||||||||
| Divisions: | 02-Fakultas Keguruan dan Ilmu Pendidikan 02-Fakultas Keguruan dan Ilmu Pendidikan > 83201-Jurusan Pendidikan Vokasional Teknik Elektro |
|||||||||
| Depositing User: | Mr Gigih Priyogi Gigih | |||||||||
| Date Deposited: | 23 Feb 2024 11:50 | |||||||||
| Last Modified: | 23 Feb 2024 16:45 | |||||||||
| URI: | http://eprints.untirta.ac.id/id/eprint/33383 |
Actions (login required)
 |
View Item |