Penerapan Algoritma Convolutional Neural Network dan Haar Cascade Untuk Presensi Dengan Video Rekaman Zoom

Muhammad Verdiansyah; Achmad Solichin

doi:10.35316/jimi.v7i2.116-127

Muhammad Verdiansyah Universitas Budi Luhur
Achmad Solichin Universitas Budi Luhur

10.35316/jimi.v7i2.116-127

Abstract

The COVID-19 pandemic that is engulfing the world is one of the situations that urges the use of and even human dependence on technology to become higher. This pandemic that can cause death by spreading through droplets or water droplets, so many countries have implemented social restrictions by prohibiting their citizens from doing many activities outside. The use of technology such as the Google Meet and Zoom applications has become a new habit for the community, especially in learning and teaching. Attendance is important to know and control the presence of students in the teaching and learning process. Currently, attendance at online lectures is still mostly done by calling students one by one or asking students to fill out certain forms. It has weaknesses and is less effective. Therefore, this study proposes presence with face identification using a web-based application system. The method used in this research are Haar Cascade face detection for facial image extraction and Convolutional Neural Network (CNN) algorithm for face identification process. The contribution given from this research in the form of identification can be done using video recordings of zoom and images or screenshots from zoom and displaying student attendance. In this study, the dataset was sourced from taking photos directly on individuals. There are 20 labels used in this study. The identification results of 1119 facial images (test data) on the CNN custom model, obtained 88% accuracy, 88% precision, and 83% recall.

Downloads

Download data is not yet available.

References

World Health Organization, “Coronavirus disease (COVID-19),” 2022. .

W. H. L. Stevany Afrizal1, Septi Kuntari, Rizki Setiawan, “Perubahan Sosial Pada Budaya Digital Dalam Pendidikan Karakter Anak,” Pros. Semin. Nas. Pendidik. FKIP, vol. 3, no. 1, pp. 429–436, 2020.

S. Sukawati, “Pemanfaatan Zoom Meeting Dan Google Classroom Dalam Mata Kuliah Inovasi,” Semantik, vol. 10, no. 1, pp. 45–54, 2021.

G. Aprilian Anarki, K. Auliasari, and M. Orisa, “Penerapan Metode Haar Cascade Pada Aplikasi Deteksi Masker,” JATI (Jurnal Mhs. Tek. Inform., vol. 5, no. 1, pp. 179–186, 2021.

A. Solichin and A. Harjoko, “Deteksi Pejalan Kaki pada Video dengan Metode Fastest Pedestrian Detector in The West (FPDW),” TICOM, vol. 2, no. 1, pp. 202–205, 2013.

G. S. Behera, “Face Detection with Haar Cascade,” 2020. .

Open CV, “Cascade Classifier,” 2022.

Mathworks.com, “integralImage,” 2022.

A. Desarda, “Understanding AdaBoost,” Towards Data Science, 2019. .

G. Cloud, “Advanced Guide to Inception v3,” 2022.

M. Baihaqy, A. T. Wibowo, and D. Q. Utama, “Klasifikasi Tanaman Anggrek jenis Phalaenopsis berdasarkan Citra Labellum Bunga Menggunakan Metode Convolutinal Neural Network (CNN),” e-Proceeding Eng., vol. 9, no. 3, pp. 1942–1951, 2022.