Latent codebook regression for facial feature localisation. Issue 9 (4th April 2016)

• Record Type: Journal Article
• Authors: Choi, H.C.
• Is Part Of: Electronics letters. Volume 52:Issue 9(2016)
• Page Start: 703
• Page End: 705
• Publication Date: 2016-04-04
• Subjects: feature extraction -- face recognition -- regression analysis; latent codebook regression -- facial feature localisation -- nonparametric inferring procedure -- latent feature -- nonlinear feature space -- motion vector space -- computational complexity -- mobile devices; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2015.3926
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : A new non‐parametric inferring procedure of facial feature localisation which learns regression in latent variable space is introduced. The proposed method uses regression between latent feature and motion spaces spanned by a set of bases of nonlinear feature space and motion vector space which is trained from a large sample set in codebook. Compared with the previous method of using codebook or eigen‐codebook, the proposed method achieved both a significant reduction in the memory consumption without loss of accuracy and a very low computational complexity enough to run in mobile devices.