Sistem Registrasi Dan Identifikasi Wajah Untuk Akses Fasilitas Universitas Kristen Petra Dengan Kombinasi Facenet Dan Hierarchical Navigable Small Worlds

August Berlin Tungka (Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya)

Jurnal Infra
Vol 10, No 2 (2022)

The Identity Cards of students are used to access the facilities and participate in events of Petra Christian University. The problem which arises from these cards is the misuse by the irresponsible group. For this, the university needs the face identification system as the alternative. This thesis is meant to build a fast, accurate, and easy to use face identification system. The methods used to solve the problem is a combination of Facenet and Hierarchical Navigable Small Worlds (HNSW). Facenet is used to process the face into a 128-dimension vector which will be used for searching. HNSW is a k Nearest Neighbor search method which is used in a large-scale search. Using the method, the system takes an average time of 1 second to identify faces.