Deteksi Kedipan dengan Metode CNN dan Percentage of Eyelid Closure (PERCLOS)

Lutfi Ananditya Septiandi, Eko Mulyanto Yuniarno, Ahmad Zaini
Submission Date: 2021-03-08 02:23:49
Accepted Date: 2021-08-31 08:07:48

Abstract


Pengembangan teknologi mengenai face detection dan eyes detection melaju sangat pesat, sehingga peneliti berlomba-lomba meneliti metode dan algoritma yang optimal untuk pengaplikasian di kehidupan sehari-hari, mulai dari pengamanan biometrics sampai identifikasi wajah secara au- tomasi. Di tugas akhir ini diusulkan penggunaan metode Convo- lutional Neural Network (CNN) dan Percentage of Eyelid Closure (PERCLOS) pada pendeteksi kedipan mata. Sistem dibangun menggunakan webcam personal computer sebagai kamera dan mendeteksi secara real-time. Sistem dapat mengenali kondisi ketika mata tertutup atau mata terbuka dan menentukan lebar bukaan mata dengan menggunakan Eye Aspect Ratio (EAR) serta dapat mengestimasi skor tatapan dengan menggunakan Percentage of Eyelid Closure (PERCLOS). Sistem dapat menge- nali wajah dari objek bukan wajah dengan jarak pendeteksian optimal antara 40-70 cm. Model hasil training dapat mengk- lasifikasikan kondisi mata terbuka dan mata tertutup dengan menggunakan Convolutional Neural Network dengan arstitektur yang memiliki 3 layer mendapatkan hasil accuracy 98% dan loss 2.05%

Keywords


face detection; eyes detection; Convolutional Neural Network (CNN), Eye Aspect Ratio (EAR); Percentage of Eyelid Closure (PERCLOS)

Full Text: PDF

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).

Refbacks

  • There are currently no refbacks.


Creative Commons License
Jurnal Teknik ITS by Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-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.
Statistik Pengunjung