Nearest neighbor weighted average customization for modeling faces
Yükleniyor...
Dosyalar
Tarih
2013-10
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In this paper, we present an anatomically accurate generic wireframe face model and an efficient customization method for modeling human faces. We use a single 2D image for customization of the generic model. We employ perspective projection to estimate 3D coordinates of the 2D facial landmarks in the image. The non-landmark vertices of the 3D model are shifted using the translations of k nearest landmark vertices, inversely weighted by the square of their distances. We demonstrate on Photoface and Bosphorus 3D face data sets that the proposed method achieves substantially low relative error values with modest time complexity.
Açıklama
Anahtar Kelimeler
Face modeling, Customization, Active shape model, Perspective projection, Procrustes analysis, Shape models, 3D, Recognition, Tracking, Robust
Kaynak
Machine Vision and Applications
WoS Q Değeri
Q2
Scopus Q Değeri
Q2
Cilt
24
Sayı
7
SI
SI
Künye
Abeysundera, H. P., Benli, K. S. & Eskil, M. T. (2013). Nearest neighbor weighted average customization for modeling faces. Machine Vision and Applications, 24(7), 1525-1537. doi:10.1007/s00138-013-0489-x
