Similarity: Design of Real-Time Face Recognition and Emotion Recognition on Humanoid Robot Using Deep Learning

Dwijayanti, Suci (2023) Similarity: Design of Real-Time Face Recognition and Emotion Recognition on Humanoid Robot Using Deep Learning. ithenticate universitas sriwijaya.

[thumbnail of Design_of_Real_Time_Face_Recognition_and_Emotion_R.pdf] Text
Design_of_Real_Time_Face_Recognition_and_Emotion_R.pdf

Download (2MB)

Abstract

A robot is capable of mimicking human beings, including recognizing their faces and emotions. However, current studies of the humanoid robot have treated face recognition and emotion recognition as separate problems. Thus, this study proposed a combination of face and emotion recognition implemented in the real-time system. Face and emotion recognition systems were developed concurrently in this study using convolutional neural network architectures. The proposed architecture was compared to the well-known architecture, AlexNet, to determine which architecture would be better suited for implementation on a humanoid robot. Primary data from 30 respondents was used for face recognition. Meanwhile, emotional data were collected from the same respondents and combined with secondary data from a 2500-person dataset. Surprise, anger, neutral, smile, and sadness were among the emotions. The experiment was carried out in real-time on a humanoid robot using the two architectures. The accuracy of face and emotion recognition using the AlexNet model was 88 % and 56 %, respectively. Meanwhile, the proposed architecture achieved accuracy rates of 96 % for face recognition and 68 % for emotion recognition, respectively. Thus, the proposed method performs better in terms of recognizing faces and emotions, and it can be implemented on a humanoid robot.

Item Type: Other
Subjects: #3 Repository of Lecturer Academic Credit Systems (TPAK) > Results of Ithenticate Plagiarism and Similarity Checker
Divisions: 03-Faculty of Engineering > 20201-Electrical Engineering (S1)
Depositing User: Ms Suci Dwijayanti
Date Deposited: 06 May 2023 01:41
Last Modified: 06 May 2023 01:41
URI: http://repository.unsri.ac.id/id/eprint/99816

Actions (login required)

View Item View Item