IDENTIFIKASI DEPRESI BERDASARKAN EKSPRESI WAJAH MENGGUNAKAN ARSITEKTUR VGGNET Depression Identification Based on Facial Expressions Using VGGNet Architecture

Prakhastama, Ipram Zanuar (2025) IDENTIFIKASI DEPRESI BERDASARKAN EKSPRESI WAJAH MENGGUNAKAN ARSITEKTUR VGGNET Depression Identification Based on Facial Expressions Using VGGNet Architecture. Undergraduate thesis, UNIVERSITAS 17 AGUSTUS 1945 SURABAYA.

Preview	Text (ABSTRAK) ABSTRAK(BARU).pdf Download (846kB) | Preview
	Text ABSTRAK.pdf Restricted to Repository staff only Download (571kB)
	Text BAB 1.pdf Restricted to Repository staff only Download (278kB)
	Text BAB 2.pdf Restricted to Repository staff only Download (841kB)
	Text BAB 3.pdf Restricted to Repository staff only Download (379kB)
	Text BAB 4.pdf Restricted to Repository staff only Download (2MB)
	Text BAB 5(BARU).pdf Restricted to Repository staff only Download (275kB)
	Text BAB 5.pdf Restricted to Repository staff only Download (217kB)
Preview	Text 1462100091_Ipram Zanuar Prakhastama_JBI.pdf Download (280kB) | Preview
Preview	Text HASIL TURNITIN.pdf Download (377kB) | Preview

Abstract

Depression is a common mental health disorder that affects various aspects of an individual's life worldwide. Many cases of depression go undiagnosed in a timely manner due to traditional methods such as clinical interviews and questionnaires, which are time-consuming and prone to subjective bias. With the advancement of technology, computer vision-based approaches have made it increasingly possible to detect depression automatically, efficiently, and objectively. This research explores the VGG19 model to detect depression through facial expression images. The implementation uses the FER2013 dataset, which is re-categorized into two classes: depression (anger, disgust, fear, sadness) and non-depression (neutral, happiness, surprise). The implementation of the best model achieved a training accuracy of 78% and a validation accuracy of 77% on test data. The model has been deployed as a web based application to assist in the visual and interactive classification of depression.

Actions (login required)

View Item