Abstract
In this paper, a single hidden-layer feedforward fusion network is proposed for face identity verification. Essentially, the feature extraction, matching score calculation and fusion algorithm design steps are integrated and absorbed into a hidden layer of the model. Each hidden node works on the raw face image directly and produces an Euclidean distance based match score within the network. These scores are then incorporated with output weights to produce a fused score at the final stage. Our experimental study conducted using three face databases shows that the proposed model consistently outperforms competing methods.
| Original language | English |
|---|---|
| Title of host publication | 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 944-948 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781479951994 |
| DOIs | |
| Publication status | Published - 2014 Jan 1 |
| Event | 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014 - Singapore, Singapore Duration: 2014 Dec 10 → 2014 Dec 12 |
Other
| Other | 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014 |
|---|---|
| Country | Singapore |
| City | Singapore |
| Period | 14/12/10 → 14/12/12 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Human-Computer Interaction
- Artificial Intelligence
- Control and Systems Engineering
Cite this
}
A single layer feedforward fusion network for face verification. / Oh, Beom Seok; Oh, Kangrok; Toh, Kar Ann; Beng Jin Teoh, Andrew.
2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 944-948 7064432.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - A single layer feedforward fusion network for face verification
AU - Oh, Beom Seok
AU - Oh, Kangrok
AU - Toh, Kar Ann
AU - Beng Jin Teoh, Andrew
PY - 2014/1/1
Y1 - 2014/1/1
N2 - In this paper, a single hidden-layer feedforward fusion network is proposed for face identity verification. Essentially, the feature extraction, matching score calculation and fusion algorithm design steps are integrated and absorbed into a hidden layer of the model. Each hidden node works on the raw face image directly and produces an Euclidean distance based match score within the network. These scores are then incorporated with output weights to produce a fused score at the final stage. Our experimental study conducted using three face databases shows that the proposed model consistently outperforms competing methods.
AB - In this paper, a single hidden-layer feedforward fusion network is proposed for face identity verification. Essentially, the feature extraction, matching score calculation and fusion algorithm design steps are integrated and absorbed into a hidden layer of the model. Each hidden node works on the raw face image directly and produces an Euclidean distance based match score within the network. These scores are then incorporated with output weights to produce a fused score at the final stage. Our experimental study conducted using three face databases shows that the proposed model consistently outperforms competing methods.
UR - http://www.scopus.com/inward/record.url?scp=84949924504&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949924504&partnerID=8YFLogxK
U2 - 10.1109/ICARCV.2014.7064432
DO - 10.1109/ICARCV.2014.7064432
M3 - Conference contribution
AN - SCOPUS:84949924504
SP - 944
EP - 948
BT - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
PB - Institute of Electrical and Electronics Engineers Inc.
ER -