RANCANG BANGUN PROTOTIPE MASK RECOGNITION BERBASIS RASPBERRY PI

MARHAMMA, RIDHA (2021) RANCANG BANGUN PROTOTIPE MASK RECOGNITION BERBASIS RASPBERRY PI. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 Cover.pdf Download (380kB) | Preview
	Text (BAB I) 02 Bab 1.pdf Restricted to Registered users only Download (264kB)
	Text (BAB II) 03 Bab 2.pdf Restricted to Registered users only Download (719kB)
	Text (BAB III) 04 Bab 3.pdf Restricted to Registered users only Download (348kB)
	Text (BAB IV) 05 Bab 4.pdf Restricted to Registered users only Download (680kB)
	Text (BAB V) 06 Bab 5.pdf Restricted to Registered users only Download (229kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (285kB)

Abstract

Face recognition technology is a pattern approach to be able to identify a person by using digital image processing or image processing. There are so many innovations today that we can use to simplify our daily activities. Currently, almost the whole world is in the period of the Covid-19 Virus pandemic, which to reduce the impact of contracting the Covid-19 Virus, you must wear a mask. In this final project, a facial recognition system has been designed using the Raspberry Pi with the Mask Recognition Method. The Mask Recognition method is a technology based on Biometric Artificial Intelligence (AI) that can identify a person by analyzing patterns based on the texture and shape of a person's face that was previously stored in the database. The face recognition system dataset using masks has been trained using the MobileNet model. The accuracy value of this system is obtained by testing the system that has been designed by performing facial recognition based on light conditions, mask color, camera tone, camera distance and facial images of more than one person. From this final project, the results with the best accuracy were obtained when testing based on the color of the mask, the mask used was yellow with an average accuracy value of 96.6% and when the light conditions were bright with an average accuracy value of 93 ,3%. Keywords: Covid-19, Dataset, Image Processing, Mask Recognition, MobileNet. Teknologi pengenalan wajah merupakan pendekatan pola untuk dapat mengidentifikasi seseorang dengan menggunakan pengolahan citra digital atau image processing. Banyak sekali inovasi di masa kini yang dapat kita gunakan untuk mempermudah kegiatan sehari-hari. Saat ini hampir seluruh dunia sedang dalam masa pandemi Virus Covid-19, yang dimana untuk mengurangi dampak tertular dari Virus Covid-19 harus menggunakan masker. Pada Tugas Akhir ini telah dirancang sistem pengenalan wajah menggunakan Raspberry Pi dengan Metode Mask Recognition. Metode Mask Recognition merupakan sebuah teknologi berbasis Biometric Artificial Intelligence (AI) yang dapat mengidentifikasi seseorang dengan menganalisis pola berdasarkan tekstur dan bentuk wajah seseorang yang sebelumnya sudah tersimpan di dalam database. Dataset sistem pengenalan wajah dengan menggunakan masker sudah dilatih dengan menggunakan model MobileNet. Nilai akurasi pada sistem ini didapatkan dengan melakukan pengujian terhadap sistem yang sudah dirancacng dengan melakukan pengenalan wajah berdasarkan kondisi cahaya, warna masker, tone kamera, jarak kamera dan gambar wajah lebih dari satu orang. Dari Tugas Akhir ini didapatkan hasil pengujan dengan tingkat akurasi paling bagus didapatkan ketika pengujian berdasarkan warna masker, masker yang digunakan berwarna kuning dengan nilai rata-rata nilai akurasi sebesar 96,6% dan ketika kondisi cahaya yang terang dengan rata-rata nilai akurasi sebesar 93,3%. Kata kunci : Covid-19, Dataset, Image Processing, Mask Recognition, MobileNet.

Actions (login required)

View Item