Identifikasi Emosi Melalui Citra Ekspresi Wajah Menggunakan Metode Faster R-CNN

Prakoso, Teddy Hariyanto Premadi (2022) Identifikasi Emosi Melalui Citra Ekspresi Wajah Menggunakan Metode Faster R-CNN. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstrak) Abstrak.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (138kB)
	Text (Bab 1 Pendahuluan) Bab 1.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (83kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (75kB)

Abstract

The word “emotion” in KBBI (Kamus Besar Bahasa Indonesia) means a feeling through up and down in a short time. Emotions described by a person unconsciously through several ways such as movement, voice, and facial expressions. Facial expressions are the result of facial muscle movement which is a way of non-verbal communication in expresssing the feelings or emotions. This study applies the Faster R-CNN method which is considered faster in detecting objects compared to the previous methods like R-CNN and Fast R-CNN. In this study, facial expressions picture will be used to detect emotions with four (4) division of emotional classes namly angry, happy, neutral, and sad. Testing’s flow is conducted in two ways, namely using a testing image that’s already resized and a random image without resizing process. The result of the test without resize process achieve accuracy only on 52,5% then the test using resized image showed accuracy value on 82,5%. Research that related to emotion identification can be developed by applied to something more useful in people’s life such as robots or computers that could be understand people feelings or emotion based on their facial expression.

Actions (login required)

View Item