Multilinear subspace learning using handcrafted and deep features for face kinship verification in the wild
- PDF / 2,577,853 Bytes
- 14 Pages / 595.224 x 790.955 pts Page_size
- 5 Downloads / 231 Views
Multilinear subspace learning using handcrafted and deep features for face kinship verification in the wild Mohcene Bessaoudi1 · Ammar Chouchane2 · Abdelmalik Ouamane1 · Elhocine Boutellaa3 Accepted: 26 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, we propose a new multilinear and multiview subspace learning method called Tensor Cross-view Quadratic Discriminant Analysis for face kinship verification in the wild. Most of the existing multilinear subspace learning methods straightforwardly focus on learning a single set of projection matrices, making it difficult to separate different classes. To address this issue, the proposed approach mutually learns multi-view representations for multidimensional cross-view matching. In order to decrease the effect of the within class variations for each mode of the tensor data, the proposed approach integrates the Within Class Covariance Normalization. Moreover, we propose a new tensor face descriptor based on the Gabor wavelets. Besides, we investigate the complementarity of handcrafted and deep face tensor features via their fusion at score level using the Logistic Regression method. Our extensive experiments demonstrate that the proposed kinship verification framework outperforms the state of the art, achieving 95.14%, 91.83% and 93.58% verification accuracies on Cornell KinFace, UB KinFace and TSKinFace face kinship datasets, respectively. Keywords Kinship verification · Multilinear subspace learning · Multi-view representation · Tensors · local features · Hist-Gabor.
1 Introduction Nowadays, automatic kinship verification from human face images is one of the most challenging research topics. The goal of kinship verification is to check the existence of a particular relationship between two individuals by visually comparing their facial appearances [5, 9, 12, 13, 46]. Checking human kin relationship based on faces is challenging because of the high level of appearance variability due to several effects such as hereditary contrast, gender distinction and age gap. There are numerous interesting real life applications for kinship verification such as family photographs organization, finding missing relatives, forestalling child trafficking, etc. Video surveillance and tracking systems are typical systems where the face-based family relationship checking can be deployed. In Mohcene Bessaoudi
[email protected] 1
Laboratory of LI3C, University of Biskra, Biskra, Algeria
2
University of Yahia Fares Medea, M´ed´ea, Algeria
3
Telecommunication division, Centre de D´eveloppement des Technologies Avanc´ees, Algiers, Algeria
spite of the fact that a DNA test is the most exact approach for kinship verification [15], it lamentably cannot be utilized in several situations. Hence, face based kinship verification emerges as a potential alternative compared to the DNA. Various computer vision approaches have been proposed to address the kinship verification challenge. Among the most viable literature works are le
Data Loading...
