Facial Feature Embedded Cyclegan For Vis-Nir Translation

  title={Facial Feature Embedded Cyclegan For Vis-Nir Translation},
  author={Huijiao Wang and Li Wang and Xulei Yang and Lei Yu and Haijian Zhang},
  journal={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  • Huijiao Wang, Li Wang, +2 authors Haijian Zhang
  • Published 20 April 2019
  • Computer Science
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Visible and near-infrared (VIS-NIR) face recognition remains a challenging task due to distinctions between spectral components of two modalities. Inspired by the CycleGAN, this paper presents a method aiming to translate between VIS and NIR face images. To achieve this, we propose a new facial feature embedded CycleGAN. Firstly, to learn the particular feature while preserving common facial representation between VIS and NIR domains, we employ a general facial feature extractor (FFE) to… Expand


Transferring deep representation for NIR-VIS heterogeneous face recognition
A deep TransfeR NIR-VIS heterogeneous face recognition neTwork (TRIVET) with deep convolutional neural network with ordinal measures to learn discriminative models achieves state-of-the-art recognition performance on the most challenging CASIA Nir-VIS 2.0 Face Database. Expand
Matching NIR Face to VIS Face Using Transduction
This work proposes a transduction method named transductive heterogeneous face matching (THFM) to adapt the VIS-NIR matching learned from training with available image pairs to all people in the target set, and proposes a simple feature representation for effective VIS-nIR matching. Expand
Learning Invariant Deep Representation for NIR-VIS Face Recognition
A deep convolutional network approach that uses only one network to map both NIR and VIS images to a compact Euclidean space and achieves 94% verification rate at FAR=0.1% on the challenging CASIA NIR-VIS 2.0 face recognition dataset. Expand
Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-Spectral Hallucination and Low-Rank Embedding
This paper proposes an approach to extend the deep learning breakthrough for VIS face recognition to the NIR spectrum, without retraining the underlying deep models that see only VIS faces, and obtains state-of-the-art accuracy on the CASIA NIR-VIS v2.0 benchmark. Expand
Coupled Spectral Regression for matching heterogeneous faces
  • Zhen Lei, S. Li
  • Computer Science
  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
This paper presents a subspace learning framework named Coupled Spectral Regression (CSR) to solve the challenge problem of coupling the two types of face images and matching between them, and shows that the proposed CSR method significantly outperforms the existing methods. Expand
NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction
This paper develops a method to reconstruct VIS images in the NIR domain and vice-versa using a cross-spectral joint ℓ0 minimization based dictionary learning approach to learn a mapping function between the two domains. Expand
Facial expression recognition from near-infrared videos
A novel research on a dynamic facial expression recognition, using near-infrared (NIR) video sequences and LBP-TOP feature descriptors and component-based facial features are presented to combine geometric and appearance information, providing an effective way for representing the facial expressions. Expand
Pose-preserving Cross Spectral Face Hallucination
This work presents an approach to avert the data misalignment problem and faithfully preserve pose, expression and identity information during cross-spectral face hallucination and outperforms current state-of-the-art HFR methods at a high resolution. Expand
Learning mappings for face synthesis from near infrared to visual light images
A novel method for synthesizing VIS images from NIR images based on learning the mappings between images of different spectra is proposed, which reduces the inter-spectral differences significantly, thus allowing effective matching between faces taken under different imaging conditions. Expand
Residual Compensation Networks for Heterogeneous Face Recognition
This paper proposes a new two-branch network architecture, termed as Residual Compensation Networks (RCN), to learn separated features for different modalities in HFR, which outperforms other state-of-the-art methods significantly. Expand