TY - JOUR
T1 - Efficient deep discriminant embedding
T2 - Application to face beauty prediction and classification
AU - Dornaika, F.
AU - Moujahid, A.
AU - Wang, K.
AU - Feng, X.
N1 - Publisher Copyright:
© 2020 Elsevier Ltd
PY - 2020/10
Y1 - 2020/10
N2 - Inspired by deep learning architectures, we introduce a multi-layer local discriminant embedding algorithm that integrates feature selection as a main step to capture the most relevant and discriminant features of an input face image or face descriptor. The proposed framework allows to transform any linear method to a deep variant via a cascaded feature extraction and selection architecture able to convert weak and noisy descriptors to strong ones. As a case study, the local discriminant embedding (LDE) projection is adopted as a linear feature extraction method. The resulting framework can be considered as an efficient deep discriminant embedding technique. To validate this framework, we have considered two different computer vision problems: face beauty prediction which involves both classification and regression tasks, and face recognition which is a classical classification problem. Experiments conducted on different public benchmark databases show that this approach enhances the performance of the LDE algorithm and provides a discriminating strategy to solve the dimensionality reduction problem. For face beauty regression, our proposed framework achieved on average an improvement of about 5% and 7% with respect to two other configurations where only VGG-face and VGG-face followed by LDE have been considered. For face beauty classification, the proposed algorithm outperformed many classical manifold learning techniques reaching in some databases improvements of about 10%.
AB - Inspired by deep learning architectures, we introduce a multi-layer local discriminant embedding algorithm that integrates feature selection as a main step to capture the most relevant and discriminant features of an input face image or face descriptor. The proposed framework allows to transform any linear method to a deep variant via a cascaded feature extraction and selection architecture able to convert weak and noisy descriptors to strong ones. As a case study, the local discriminant embedding (LDE) projection is adopted as a linear feature extraction method. The resulting framework can be considered as an efficient deep discriminant embedding technique. To validate this framework, we have considered two different computer vision problems: face beauty prediction which involves both classification and regression tasks, and face recognition which is a classical classification problem. Experiments conducted on different public benchmark databases show that this approach enhances the performance of the LDE algorithm and provides a discriminating strategy to solve the dimensionality reduction problem. For face beauty regression, our proposed framework achieved on average an improvement of about 5% and 7% with respect to two other configurations where only VGG-face and VGG-face followed by LDE have been considered. For face beauty classification, the proposed algorithm outperformed many classical manifold learning techniques reaching in some databases improvements of about 10%.
KW - Classification
KW - Dimensionality reduction
KW - Discriminant embedding
KW - Feature subset selection
KW - Image-based face beauty analysis
KW - Manifold learning
KW - Multi-layer architecture
UR - http://www.scopus.com/inward/record.url?scp=85088903978&partnerID=8YFLogxK
U2 - 10.1016/j.engappai.2020.103831
DO - 10.1016/j.engappai.2020.103831
M3 - 文章
AN - SCOPUS:85088903978
SN - 0952-1976
VL - 95
JO - Engineering Applications of Artificial Intelligence
JF - Engineering Applications of Artificial Intelligence
M1 - 103831
ER -