Text

PERANCANGAN SISTEM PENGENALAN WAJAH DAN EMOSI PADA HUMANOID ROBOT SECARA REAL TIME BERBASIS DEEP LEARNING

---

Penilaian

---

A robot has the capability to mimic human beings, including recognizing their face and emotion. However, the current studies have not been implemented in the real-time system of the humanoid robot. In addition, face recognition and emotion recognition have been considered separate problems. Thus, this study proposed a combination of face recognition and emotion recognition for real-time application on a humanoid robot. In this study, face and emotion recognition systems were developed simultaneously using convolutional neural network architectures. Own model was compared to the well-known architecture, such as AlexNet architecture and Vgg16 to find out which architecture is better to be implemented on a humanoid robot. Data used for face recognition were primary data taken from 30 respondents of electrical engineering students after that data will be preprocessed so that the result in total data of 18900. Meanwhile, the emotional data consisting of surprise, anger, neutral, smile, and sad were also taken from the same respondents combined with secondary data from a dataset with total data of 5000 data for train and test data. The test was carried out in real-time on a humanoid robot using the two architectures. The results showed that the accuracy of face and emotion recognition were 85% and 64%, respectively using the AlexNet model. Model Vgg16 with a recognition accuracy of 100% and 73%, respectively. Meanwhile, the own model architecture obtained the accuracy of 87% and 67% for face recognition and emotion recognition, respectively. Thus, model Vgg16 has better performance to recognize the face as well as the emotions, and it can be implemented on a humanoid robot.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207003271	T73898	T738982023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T738982023

Publisher

Inderalaya : Prodi Teknik Elektro, Fakultas Tenik., 2022

Collation

xiii, 89 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

629.807

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik kontrol otomatis
Prodi Teknik Elektro

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment