Pengenalan wajah merupakan salah satu teknologi biometrik yang banyak diaplikasikan terutama pada sistem keamanan. Sistem absensi dengan wajah, mengenali pelaku tindak kriminal dengan CCTV adalah beberapa aplikasi dari pengenalan wajah. Efisiensi dan akurasi menjadi faktor utama pengenalan wajah banyak diaplikasikan. Pada penelitian ini, sistem identifikasi diimplementasikan dalam bentuk pengenalan wajah 3 dimensi berbasis template matching menggunakan metode Iterative Closest Point (ICP) dan klasifikasi Support Vector Machine (SVM). Iterative Closest Point (ICP) memberikan informasi dimensi dengan meminimalisasi kesalahan antara titik-titik dalam satu tampilan dan titik terdekatnya agar template wajah 3D yang dibuat sesuai dengan citra referensi. Sedangkan SVM adalah adalah metode klasifikasi dengan menentukan kelas citra berdasarkan informasi yang diperoleh dari proses ektraksi ciri. Hasil akhir dari penelitian ini adalah suatu aplikasi yang mampu melakukan identifikasi pengenalan pola wajah 3D. Berdasarkan confusion matrix, diperoleh bahwa sistem ini bekerja dengan precision 97,30%, recall 100,00%, accuracy 97,56% pada pengambilan frame citra sebanyak 48, iterasi ke 49, partisi 12, dan menggunakan SVM tipe OAA.AbstractFace recognition is a biometric technology that is widely applied especially in the security system. Attendance systems with faces, recognizing criminals with CCTV are some of the applications of face recognition. Efficiency and accuracy are the main factors that face recognition is widely applied. In this study, the identification system was implemented in the form of 3-dimensional face recognition based on template matching using the Iterative Closest Point (ICP) method and Support Vector Machine (SVM) classification. Iterative Closest Point (ICP) provides dimensional information by minimizing errors between points in one view and the closest point so that 3D face templates are made in accordance with the reference image. Whereas SVM is a classification method by determining the image class based on information obtained from the extraction of features. The final result of this study is an application that is able to identify 3D face pattern recognition. Based on the confusion matrix, found that this system works with 97.30% precision, recall 100.00%, 97.56% accuracy in image frame capture as much as 48 iterations to 49, the partition 12, and using the SVM-type OAA.
Collaboration network of the authors
5 authors ·
6 co-authorship links
· 2 across different organisations
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
Telkom University
Bandung Institute of Technology
Different organisations
Same organisation
Affiliation unknown
Thicker line = more joint articles · bigger circle = more articles
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.