Study of WCNN:NIR-VIS Face Recognition
Keywords:
Heterogeneous Face Recognition, Deep Neural Networks, VIS-NIR Face Matching, Feature Representation.Abstract
In this survey paper we have been studying the WCNN Near infrared-visible (NIR-VIS) heterogeneous face recognition (HFR) refers to the process of matching NIR to VIS face images. The current heterogeneous methods try to extend VIS face recognition methods to the NIR spectrum by synthesizing VIS images from NIR images. It refers to matching a sample face image to a gallery of face images taken from alternate imaging modality. The major challenge of heterogeneous face recognition found in the great discrepancies between different image modalities. This survey paper having high resolution for heterogeneous face synthesis as complementary combination of two or more components. The painting component synthesizes and in paints VIS image textures from NIR image textures. The correction component maps any pose in NIR images to a frontal pose in VIS images, resulting in paired NIR and VIS textures. A warping procedure is developed to integrate the two components into an end-to-end deep network. A discriminator and wavelet based discriminator are being designed to supervise intra-class variance and visual quality respectively.
References
- Ran He , Senior Member, IEEE, Xiang Wu , Zhenan Sun , Member, IEEE, and Tieniu Tan,” Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition”
- Tiago de Freitas Pereira “Heterogeneous Face Recognition Using Domain Specific Units” Journal of Latex Class Files, vol. 14, no. 8, August 2015.
- Jie Cao “Learning a High Fidelity Pose Invariant Model for High-resolution Face Formalization” 32nd Conference on Neural Information Processing Systems (Nuri’s 2018), Montréal, Canada.
- Benjamin S. Riggan “Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks” International Journal of Computer Vision manuscript.
- Zhenan Sun “Cross-spectral Face Completion for NIR-VIS Heterogeneous Face Recognition” Journal of Latex Class Files, January 2017.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.