Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/75061
Title: Pore-scale facial features matching under 3D morphable model constraint
Authors: Zeng, X
Li, D
Zhang, Y
Lam, KM 
Keywords: 3D morphable model
3DDFA
Dataset
Pore-scale facial features
PSIFT
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
URI: http://hdl.handle.net/10397/75061
ISBN: 9789811073014
ISSN: 1865-0929
DOI: 10.1007/978-981-10-7302-1_3
Appears in Collections:Conference Paper

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

Page view(s)

12
Last Week
0
Last month
Citations as of Oct 14, 2018

Google ScholarTM

Check

Altmetric


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