Complement component face space for 3D face recognition from range images
- PDF / 3,090,184 Bytes
- 18 Pages / 595.224 x 790.955 pts Page_size
- 60 Downloads / 187 Views
Complement component face space for 3D face recognition from range images Koushik Dutta1
· Debotosh Bhattacharjee1,2 · Mita Nasipuri1 · Ondrej Krejcar2,3
Accepted: 9 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This paper proposes a mathematical model for decomposing a range face image into four basic components (named ‘complement components’) in conjunction with a simple approach for data-level fusion to generate thirty-six additional hybrid components. These forty component faces composing a new face image space called the ‘complement component face space.’ The main challenge of this work was to extract relevant features from the vast face space. Features are extracted from the four basic components and four selected hybrid components using singular value decomposition. To introduce diversity, the extracted feature vectors are fused by applying the crossover operation of the genetic algorithm using a Hamming distance-based fitness measure. Particle swarm optimization-based feature selection is employed on the fused features to discard redundant feature values and to maximize the face recognition performance. The recognition performances of the proposed feature set with a support vector machine-based classifier on three accessible and well-known 3D face databases, namely, Frav3D, Bosphorus, and Texas3D, show significant improvements over those achieved by stateof-the-art methods. This work also studies the feasibility of utilizing the component images in the complement component face space for data augmentation in convolutional neural network (CNN)-based frameworks. Keywords Complement component · Range face image · Data level fusion · Feature level fusion · Genetic algorithm · 2-stage Particle swarm optimization · Convolutional neural network
1 Introduction The human face is a popular biometric compared to other biometric traits, such as the heartbeat rate, retina, hand geometry, DNA, signature, and voice, due to the nonintrusive nature of the facial acquisition. Additionally, face images can be obtained without the targeted person knowing. Face recognition systems have a wide range of applications in the security domain, law enforcement, humancomputer interaction, etc. Some significant challenging Koushik Dutta
[email protected] 1
Computer Science and Engineering, Jadavpur University, Kolkata, India
2
Center for Basic and Applied Science, Faculty of Informatics and Management, University of Hradec Kralove, Hradec Kralove, Czech Republic
3
Malaysia-Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia
issues, such as varying expressions, poses, occlusions, and illumination conditions, make the face recognition process difficult. For recognition purposes, face images can be acquired in different modalities using an optical camera (still or video), a thermal/near-infrared camera, or a 3D scanner. Hence, various acquisition systems eventually produce either 2D visible videos or still images, 2D therm
Data Loading...
