Penerapan Metode Haar Cascade Pada Aplikasi Deteksi Masker

The use of mask is a mandatory for everyone in the pandemic regulation to prevent the spread of COVID-19 infection. This becomes a pandemic regulation for everyone, especially in public places like in traffic situation, such as pedestrian and motorcyclists. However, many motorcyclists ignore this rule or do not use the mask properly, let alone they have high risk in being infected by the virus; Thus, a computer vision-based solution is required to help monitoring it. This study aims to built a system to automatically detect the use of mask on motorcyclists. Here, we propose a YOLOv4 model, one of YOLO variants, which is popular in the object detection task and featured with a considerably high speed in real-time situation. This study also implements domain adaptation to discuss the object detection performances. Based on the experimental results in various scenarios, our model obtained average accuracy of 78.3% and IoU of 64.8% for class with_mask, average accuracy of 78.4% and IoU of 56.3% for class without_mask, and average accuracy of 87% and IoU of 55.5% for class incorrect_mask

show abstract

“…In a study conducted by Anarki et al, regarding face mask detection [7]. This study had the highest accuracy of 88.7% using Haar Cascade.…”

Section: Introductionmentioning

confidence: 67%

Mask Detection on Motorcyclists Using YOLOv4

Firdauz

Rachmawati

Sulistiyo

2023

bits

View full text Add to dashboard Cite

show abstract

“…Penelitian lain juga dilakukan oleh (Aprilian Anarki et al, 2021) untuk deteksi wajah dari gambar dan video yang menggunakan masker dengan metode haar cascade classification. Hasil penelitian ini menemukan bahwa akurasi metode haar cascade classification dalam deteksi wajah yang menggunakan masker memilik tingkat akurasi paling tinggi sebesar 88.7 % dan akurasi paling rendah sebesar 44.9%.…”

Section: Studi Pustakaunclassified

Validation of the Haar Cascade Classification Method in Face Detection

Bahit,

Nadia Putri Utami,

Heru Kartika Candra

et al. 2023

JITE

View full text Add to dashboard Cite

As technology develops, faces are used as a tool for human interaction with computers for security systems. Face detection technology can also provide convenience to users in various fields, especially security systems. However, there are problems regarding accuracy, complexity in the face recognition process so that many methods have been developed to increase the accuracy and complexity of the face detection process. This study aims to validate the haar cascade classification method in detecting faces from various shooting angles, with a distance of one meter from the camera and the respondent is free to make movements as well as various facial expressions and various lighting conditions that are different for each respondent. The results of this study found that the haar cascade classification method showed that the higher the epoch value, the lower the mean square error (MSE). This study also found that the haar cascade classification method has good accuracy for detecting faces from various angles, different lighting and different facial expressions with a maximum distance of one meter from the camera. This study provides recommendations for making face recognition applications using the haar cascade classification method because it can be used well for lighting effects, facial expressions and a maximum shooting distance of one meter.

show abstract

“…Dalam penelitiannya, Lambacing dan Ferdiansyah (2020) menggunakan raspberry pi sebagai pendeteksi masker dengan notifikasi telegram berbasis Internet of Things [3]. Sementara Anarki, dkk (2021) menerapkan metode haar cascade untuk aplikasi deteksi masker [4]. Metode deteksi lain secara otomatis adalah dengan menerapakan neural network dan deep learning.…”

Section: Pendahuluanunclassified

Sistem Pendeteksi Masker pada Pengemudi Kendaraan Menggunakan Kecerdasan Artifisial

Wikarta

Effendi

Pramono

2021

JEPIN

View full text Add to dashboard Cite

Deteksi penggunaan masker pada pengemudi kendaraan termasuk tugas klasifikasi yang dapat diselesaikan secara otomatis oleh kecerdasaan artifisial. Untuk implementasi pada perangkat mobile, arsitektur neural network MobileNetV2 dipilih dengan pertimbangan akurasi yang baik. Penambahan teknik data augmentation dan pemilihan optimizer ADAM semakin meningkatkan akurasi klasifikasi dari MobileNetV2. Proses deteksi dilakukan pada 13 foto pengemudi dengan masker dan 13 pengemudi tanpa masker. Untuk pengemudi tanpa masker, sistem pendeteksi berhasil 100%, meskipun ada salah satu kondisi saat pengemudi memakai masker di dagu, tingkat akurasi hanya sebesar 65,59%. Sedangkan untuk pengemudi tanpa masker, ada 1 foto yang salah, disebabkan oleh warna gelap yang digunakan sebagai masker, sehingga sistem pendeteksi mengklasifikasikan sebagai pengemudi tanpa masker dengan tingkat akurasi hingga 97,76%. Hasil analisis lebih dalam menunjukkan bahwa aksesoris seperti jilbab dan kacamata mempengaruhi tingkat akurasi yang dihasilkan oleh sistem pendeteksi. Sementara itu, tingkat akurasi juga lebih dipengaruhi oleh warna dari masker yang dipakai ketimbang pemilihan masker medis ataupun masker kain.

show abstract

Penerapan Metode Haar Cascade Pada Aplikasi Deteksi Masker

Cited by 15 publications

References 1 publication

Mask Detection on Motorcyclists Using YOLOv4

Mask Detection on Motorcyclists Using YOLOv4

Validation of the Haar Cascade Classification Method in Face Detection

Sistem Pendeteksi Masker pada Pengemudi Kendaraan Menggunakan Kecerdasan Artifisial

Contact Info

Product

Resources

About