An efficient face recognition approach combining likelihood-based sufficient dimension reduction and LDA
- PDF / 3,605,138 Bytes
- 30 Pages / 439.642 x 666.49 pts Page_size
- 67 Downloads / 181 Views
An efficient face recognition approach combining likelihood-based sufficient dimension reduction and LDA Abdallah Benouareth1 Received: 21 November 2019 / Revised: 21 July 2020 / Accepted: 4 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, an efficient approach is proposed for face recognition (FR) under pose and illumination variations. It is based on combining likelihood-based sufficient dimension reduction (LSDR) and linear discriminant analysis (LDA) using different facial features. LDA is a well–established technique for dimensionality reduction, while LSDR is a relatively new supervised subspace learning method based on the key concept of sufficiency, and consists of estimating a central subspace for low-dimensional representation of facial images. We show, empirically, that this combination can obviously increase the separability between face classes. The facial features that were considered here are either engineered (hand-crafted) features (e.g., discrete shearlet transform coefficients) or learned features which are obtained by retraining a deep learning-based system called FaceNet. To assess the performance of the proposed approach, different classification methods were used during the evaluation phase, namely collaborative representation based classifier (CRC), KNN, linear SVM and three regression-based classifiers (LSRC, LRC and LDRC). The extensive experiments performed on four publicly available face databases – the extended Yale B, FERET, LFW and CMU Multi-PIE– have demonstrated that, on the one hand, LSDR is an effective and efficiency dimensionality reduction technique for face recognition. Particularly, it can be used to significantly increase the performance of a deep learning-based system such as FaceNet, mainly, when training samples are insufficient. On the other hand, its combination with LDA can outperform best individual face recognition algorithm based on LSDR or LDA. Furthermore, the proposed approach compares favorably to current state-of-the-art methods on face recognition, in terms of classification accuracy, under illumination and pose variations. Keywords Face recognition · Sufficient dimension reduction (SDR) · Linear discriminant analysis (LDA) · Deep learning and engineered features · Learned-features · Sufficient features · Discriminative sufficient features Abdallah Benouareth
[email protected] 1
LabGed Laboratory, Computer Science Department, Badji Mokhtar University, BP 12, 23000 Annaba, Algeria
Multimedia Tools and Applications
1 Introduction Face recognition (FR) is a visual biometric process by which a captured face image can be identified (who is this person) or verified (is this the same person) from stored database of faces. It has been an active area of research in computer vision and pattern recognition since many decades ago. Related applications include biometrics, information security, access control, law enforcement, smart cards and monitoring systems. Face recognition approaches can be roughly cate
Data Loading...
