Please use this identifier to cite or link to this item:
Title: Pore-scale facial features matching under 3D morphable model constraint
Authors: Zeng, X
Li, D
Zhang, Y
Lam, KM 
Keywords: 3D morphable model
Pore-scale facial features
Issue Date: 2017
Publisher: Springer Verlag
Source: Communications in computer and information science, 2017, v. 772, p. 29-39 How to cite?
Journal: Communications in computer and information science 
Abstract: Similar to irises and fingerprints, pore-scale facial features are effective features for distinguishing human identities. Recently, the local feature extraction based on deep network architecture has been proposed, which needs a large dataset for training. However, there are no large databases for pore-scale facial features. Actually, it is hard to set up a large pore-scale facial-feature dataset, because the images from existing high-resolution face databases are uncalibrated and nonsynchronous, and human faces are nonrigid. To solve this problem, we propose a method to establish a large pore-to-pore correspondence dataset. We adopt Pore Scale-Invariant Feature Transform (PSIFT) to extract pore-scale facial features from face images, and use 3D Dense Face Alignment (3DDFA) to obtain a fitted 3D morphable model, which is constrained by matching keypoints. From our experiments, a large pore-to-pore correspondence dataset, including 17,136 classes of matched pore-keypoint pairs, is established.
Description: 2nd Chinese Conference on Computer Vision, CCCV 2017, Tianjin, China, 11-14 October, 2017
ISBN: 9789811073014
ISSN: 1865-0929
DOI: 10.1007/978-981-10-7302-1_3
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Last Week
Last month
Citations as of Oct 14, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.