Clustering Titik Fitur Model Wajah 3D Menggunakan K-Nearest Neighbour
Article Sidebar
Main Article Content
Abstract
The first step in the process of transferring animation using motion capture data to a 3D face model is to determine the facial feature points and the relationship between these points to form a 3D facial model motion system. This study focuses on grouping facial feature points where 33 centroids have been determined and looking for their association with other feature points. The 3D face model used is a humanoid character face model which is similar to a human 3D face model. The results obtained are the distribution of facial feature points that will be used as a reference in the mesh deformation process using linear blend skinning.
Langkah awal dalam proses transfer animasi menggunakan data motion capture kepada model wajah 3D adalah menentukan titik fitur wajah dan keterkaitan antar titik tersebut supaya membentuk sistem gerak model wajah 3D. Penelitian ini berfokus pada pengelompokan titik fitur wajah dimana sudah ditentukan 33 titik pusat (centroid) dan mencari keterkaitannya dengan titik fitur lainya. Model wajah 3D yang digunakan berupa model wajah karakter humanoid yang mana mempunyai kemiripan dengan model wajah 3D manusia. Hasil yang didapatkan berupa sebaran titik fitur wajah yang akan digunakan sebagai acuan dalam proses mesh deformation menggunakan linear blend skinning
Article Details

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.