Claim Missing Document
Check
Articles

Found 1 Documents
Search

Pengembangan Sistem Cermin Cerdas dengan Fitur Rekomendasi Gaya Rambut Berbasis Metode Machine Learning Wahyu Tri Admaja; Patah Herwanto
Reslaj: Religion Education Social Laa Roiba Journal Vol. 7 No. 7 (2025): RESLAJ: Religion Education Social Laa Roiba Journal
Publisher : Intitut Agama Islam Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/reslaj.v7i7.8115

Abstract

Entering the modern era, at least changing the lifestyle of every human being, especially changes in appearance. Appearance is now a need that is considered important for society, including for men. A good appearance will make someone more confident in carrying out daily activities.[1]⁠ In appearance, hair is an important thing in appearance. In this modern era, hairstyles are increasingly diverse models. So, many teenage men have difficulty determining the right hairstyle.[2]⁠ Smart mirror is an interactive technology innovation that combines facial recognition system and artificial intelligence to provide a more personalized user experience. This study aims to develop a smart mirror system that is able to recommend hairstyles according to the user's face shape using machine learning methods. The system is designed by utilizing a camera as input for facial images, a facial shape classification module based on facial landmarks, and a hairstyle recommendation module. This simulation application is supported by a wide variety of hair model options that users can try.[3]⁠ The classification process is carried out by measuring the ratio of facial dimensions to determine the category of face shape, such as oval, round, oblong, square, and others. After classification, the system automatically displays the most appropriate hairstyle suggestions through the face shape that has been detected web-based. The test results show that the system can recognize faces and can provide hairstyle recommendations with a fairly good level of accuracy in limited environments.