Abstract
Sparse-representation is well-known for its promising performance in face recognition task. Recently, researchers have focused on optimizing the dictionary by learning the discriminative sparse model. On the other hand, symmetric positive definite (SPD) matrix descriptor has spurred great interest among computer vision community due to its inherent merits that enables features fusion. However SPD descriptors form a curved-geometry known as Tensor Manifold, which is incompatible to traditional vector-based dictionary learning methods. In order to close the gap between dictionary learning and SPD matrices, this paper proposes Tensor kernel supervised dictionary learning (TKSDL) for face recognition. TKSDL works in such a way by embedding the Tensor manifold into reproducing kernel Hilbert spaces by means of Tensor kernel functions. The discriminative dictionary is then learned by maximizing the Hilbert Schmidt independence criterion (HSIC) that leverages the class labels from the training data. Sparse coefficients are solved independently from the dictionary learning via a soft thresholding mechanism. Extensive experiments on the ORL, AR and FERET datasets are conducted to verify the efficiency of the proposed methods.
| Original language | English |
|---|---|
| Title of host publication | 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 623-629 |
| Number of pages | 7 |
| ISBN (Electronic) | 9789881476807 |
| DOIs | |
| Publication status | Published - 2016 Feb 19 |
| Event | 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong Duration: 2015 Dec 16 → 2015 Dec 19 |
Other
| Other | 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 |
|---|---|
| Country | Hong Kong |
| City | Hong Kong |
| Period | 15/12/16 → 15/12/19 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Modelling and Simulation
- Signal Processing
Cite this
}
Tensor kernel supervised dictionary learning for face recognition. / Lee, Yeong Khang; Low, Cheng Yaw; Beng Jin Teoh, Andrew.
2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 623-629 7415344.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Tensor kernel supervised dictionary learning for face recognition
AU - Lee, Yeong Khang
AU - Low, Cheng Yaw
AU - Beng Jin Teoh, Andrew
PY - 2016/2/19
Y1 - 2016/2/19
N2 - Sparse-representation is well-known for its promising performance in face recognition task. Recently, researchers have focused on optimizing the dictionary by learning the discriminative sparse model. On the other hand, symmetric positive definite (SPD) matrix descriptor has spurred great interest among computer vision community due to its inherent merits that enables features fusion. However SPD descriptors form a curved-geometry known as Tensor Manifold, which is incompatible to traditional vector-based dictionary learning methods. In order to close the gap between dictionary learning and SPD matrices, this paper proposes Tensor kernel supervised dictionary learning (TKSDL) for face recognition. TKSDL works in such a way by embedding the Tensor manifold into reproducing kernel Hilbert spaces by means of Tensor kernel functions. The discriminative dictionary is then learned by maximizing the Hilbert Schmidt independence criterion (HSIC) that leverages the class labels from the training data. Sparse coefficients are solved independently from the dictionary learning via a soft thresholding mechanism. Extensive experiments on the ORL, AR and FERET datasets are conducted to verify the efficiency of the proposed methods.
AB - Sparse-representation is well-known for its promising performance in face recognition task. Recently, researchers have focused on optimizing the dictionary by learning the discriminative sparse model. On the other hand, symmetric positive definite (SPD) matrix descriptor has spurred great interest among computer vision community due to its inherent merits that enables features fusion. However SPD descriptors form a curved-geometry known as Tensor Manifold, which is incompatible to traditional vector-based dictionary learning methods. In order to close the gap between dictionary learning and SPD matrices, this paper proposes Tensor kernel supervised dictionary learning (TKSDL) for face recognition. TKSDL works in such a way by embedding the Tensor manifold into reproducing kernel Hilbert spaces by means of Tensor kernel functions. The discriminative dictionary is then learned by maximizing the Hilbert Schmidt independence criterion (HSIC) that leverages the class labels from the training data. Sparse coefficients are solved independently from the dictionary learning via a soft thresholding mechanism. Extensive experiments on the ORL, AR and FERET datasets are conducted to verify the efficiency of the proposed methods.
UR - http://www.scopus.com/inward/record.url?scp=84986208841&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84986208841&partnerID=8YFLogxK
U2 - 10.1109/APSIPA.2015.7415344
DO - 10.1109/APSIPA.2015.7415344
M3 - Conference contribution
SP - 623
EP - 629
BT - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -