Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR)

Muhammad Fachrurrozi (Universitas Sriwijaya)
Saparudin Saparudin (Universitas Sriwijaya)
Erwin Erwin (Universitas Sriwijaya)
Mardiana Mardiana (Universitas Sriwijaya)
Clara Fin Badillah (Universitas Sriwijaya)
Junia Erlina (Universitas Sriwijaya)
Auzan Lazuardi (Universitas Sriwijaya)

International Journal of Electrical and Computer Engineering
Vol 8, No 5: October 2018

Face recognition system in real time is divided into three processes, namely feature extraction, clustering, detection, and recognition. Each of these stages uses different methods, Local Binary Pattern (LBP), Agglomerative Hierarchical Clustering (AHC) and Euclidean Distance. Multi-face image search using Content Based Image Retrieval (CBIR) method. CBIR performs image search by image feature itself. Based on real time trial results, the accuracy value obtained is 61.64%.