Access Restriction

Author Heng Yang ♦ Xuming He ♦ Xuhui Jia ♦ Patras, I.
Sponsorship IEEE Signal Processing Society
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©1992
Language English
Subject Domain (in DDC) Natural sciences & mathematics ♦ Physics ♦ Electricity & electronics
Subject Keyword Face ♦ Shape ♦ Adaptation models ♦ Robustness ♦ Radio frequency ♦ Estimation ♦ Training ♦ model adaptation ♦ Face alignment ♦ occlusion ♦ random forest ♦ cascaded pose regression ♦ model adaptation ♦ Face alignment ♦ occlusion ♦ random forest ♦ cascaded pose regression
Abstract Face alignment has been well studied in recent years, however, when a face alignment model is applied on facial images with heavy partial occlusion, the performance deteriorates significantly. In this paper, instead of training an occlusion-aware model with visibility annotation, we address this issue via a model adaptation scheme that uses the result of a local regression forest (RF) voting method. In the proposed scheme, the consistency of the votes of the local RF in each of several oversegmented regions is used to determine the reliability of predicting the location of the facial landmarks. The latter is what we call regional predictive power (RPP). Subsequently, we adapt a holistic voting method (cascaded pose regression based on random ferns) by putting weights on the votes of each fern according to the RPP of the regions used in the fern tests. The proposed method shows superior performance over existing face alignment models in the most challenging data sets (COFW and 300-W). Moreover, it can also estimate with high accuracy (72.4% overlap ratio) which image areas belong to the face or nonface objects, on the heavily occluded images of the COFW data set, without explicit occlusion modeling.
Description Author affiliation :: Univ. of Hong Kong, Hong Kong, China
Author affiliation :: Australian Nat. Univ., Canberra, ACT, Australia
Author affiliation :: Queen Mary, Univ. of London, London, UK
ISSN 10577149
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2015-01-01
Publisher Place U.S.A.
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Volume Number 24
Issue Number 8
Size (in Bytes) 4.30 MB
Page Count 11
Starting Page 2393
Ending Page 2403

Source: IEEE Xplore Digital Library