<p>Abstrak. Pada dasarnya sebuah password diciptakan sebagai pengaman akun seseorang pungguna. Akan tetapi banyak password yang terlalu lemah atau mudah ditebak dan menggunakan karakter yang sama pada semua akun yang dimilikinya hal itu membuat sangat rentan terhadap pembajakan. Face recognition merupakan salah satu teknologi biometrics yang telah dipelajari dan dikembangkan banyak oleh para ahli, dimana perangkat tersebut menggunakan algoritma pengenalan wajah untuk membedakan individu yang satu dengan yang lainya berdasarkan data yang sudah ada. Penelitian ini dilakukan untuk mengimplementasikan Metode Local Binary Pattern Histogram. Hasil penelitian menggunakan motode LBPH, akurasi tertinggi didapat dari percobaan menggunakan intensitas yang sama antara citra masukan dengan citra acuan dimulai dari 15lux yang menghasilkan FAR sebesar 10% dan FRR 0% sehingga menghasilkan akurasi 92%. Uji coba dengan intensitas cahaya 30lux menghasilkan FAR 0% dan FRR 0% sehingga menghasilkan akurasi sebersar 100%. Percobaan dengan intensitas cahaya 60lux menghasilkan FAR 0% dan FRR 0% sehingga menghasilkan akurasi 100%. Kata Kunci: Login, Metode LBPH, OpenCV, Python, Pengenalan Wajah <br /> <br />Abstract. Basically, a password is created to protect a user's account. However, many passwords are too weak or easy to guess and use the same characters on all of their accounts making them very vulnerable to hijacking. Face recognition is a biometrics technology that has been studied and developed by many experts, where the device uses facial recognition algorithms to differentiate between individuals based on existing data. This research was conducted to implement the Local Binary Pattern Histogram Method. The results of the study using the LBPH method, the highest accuracy was obtained from the experiment using the same intensity between the input image and the reference image starting from 15lux which produced a FAR of 10% and FRR of 0%, resulting in an accuracy of 92%. Experiments with a light intensity of 30lux produced 0% FAR and 0% FRR, resulting in an accuracy of 100%. Experiments with a light intensity of 60lux produced 0% FAR and 0% FRR, resulting in 100% accuracy. Keywords: Login, LBPH Method, OpenCV, Python, Face Recognition</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.