Deteksi Suhu Melalui Citra Termal Wajah Menggunakan Deep Learning
Submission Date: 2021-08-15 18:27:29
Accepted Date: 2021-12-22 11:50:11
Abstract
Dalam masa pandemi kasus penularan virus CORONA masih tetap bertambah dari hari ke hari. Salah satu gejala yang umum dialami oleh pasien COVID-19 adalah demam. Hal yang umum dilakukan untuk mengukur suhu di masa pandemi adalah menggunakan termometer non kontak. Deep Learning bisa digunakan untuk mendeteksi wajah dan membantu mendeteksi suhu maksimal wajah dari gambar termal. Tujuan Penelitian ini adalah membuat aplikasi pendeteksi suhu pada citra termal menggunakan pendekatan Deep Learning. Dalam Penelitian ini dilatih sebuah model deteksi SSD-MobileNet untuk mendeteksi area wajah dari citra termal. Setelah terdeteksi, data suhu diekstrak dari area wajah tersebut. Dalam pelaksanaan penelitian ini digunakan dataset citra termal Tuft Face Database, IRDatabase, dan citra termal yang diambil menggunakan Flir One. Dari hasil uji coba didapatkan hasil mean average precision deteksi wajah sebesar 0,95 dengan threshold dari evaluasi model untuk IoU 0,75 sebesar 0,95 dan mean absolute error deteksi suhu sebesar 1,51.
Keywords
Deteksi Suhu; Deep Learning; SSD-Mobilenet; Citra termal
CC Licencing
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.
Jurnal Teknik ITS by Direktorat Riset dan Pengabdian Masyarakat (DRPM) ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/teknik.