Text

PENGENALAN CITRA WAJAH DAN IDENTIFIKASI SUHU TUBUH DENGAN CITRA TERMAL MENGGUNAKAN ALGORITMA DEEP LEARNING

---

Penilaian

---

Body temperature is a symptom that can be used to indicate someone suffered from COVID-19 when his temperature exceeds the normal temperature. To ease the separation of groups of health people from those who are above normal temperature, face recognition can be used to recognize someone contactless. Thermal image of face can be used as an approach to not only perform face recognition, but also obtain the body temperature. This study compares the XEAST XE-27 thermal imager modes used, namely mode 2, mode 3 and mode 4. The number of thermal images used in this research were 1500 images for each thermal imager mode. Face recognition process was performed using a convolutional neural network (CNN). Meanwhile, the process of extracting body temperature from thermal images was performed using the minimum and maximum temperature of each mode and class. Based on the results of the trained network, the best architecture model of CNN is using 64 filters, 5x5 kernel size, mean squared error (MSE) as loss function, learning rate 0.001 dan root mean square propagation (RMSprop) as optimizer. The accuracy result of the face recognition system in mode 2, mode 3 and mode 4 are 86,67%, 91,33% and 94,33%, respectively. While, the accuracy of body temperature extraction in mode 2, mode 3, and mode 4 were 70%, 60% and 40%, respectively. This result shows that thermal images can be used to know the body temperature and CNN can recognize person’s identity through the thermal image.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002841	T51106	T511062021	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T511062021

Publisher

Inderalaya : Jurusan Teknik Elektro, Fakultas Teknik Universitas Sriwijaya., 2021

Collation

xv, 98 hlm,: tab,: ilus,: 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

620.009 207

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Elektro
Ahli Teknologi

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment