Robust Face Recognition via Multimodal Deep Face Representation

@article{Ding2015RobustFR,
  title={Robust Face Recognition via Multimodal Deep Face Representation},
  author={Changxing Ding and Dacheng Tao},
  journal={IEEE Transactions on Multimedia},
  year={2015},
  volume={17},
  pages={2049-2058}
}
Face images appearing in multimedia applications, e.g., social networks and digital entertainment, usually exhibit dramatic pose, illumination, and expression variations, resulting in considerable performance degradation for traditional face recognition algorithms. [] Key Method The set of CNNs extracts complementary facial features from multimodal data. Then, the extracted features are concatenated to form a high-dimensional feature vector, whose dimension is compressed by SAE.

A Proposed Framework: Face Recognition With Deep Learning

This paper contributes to actualization of a propose CNN based on a pre-trained VGG Face for face recognition from set of faces tracked in video or image capture achieving a 97% accuracy.

Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks

The design details of a deep learning system for unconstrained face recognition, including modules for face detection, association, alignment and face verification are presented and some open issues regarding DCNNs for face verification problems are discussed.

Patch strategy for deep face recognition

A new layer to embed the patch strategy in convolutional architectures to improve the effectiveness of face representation and achieves comparable performance with other state-of-the-art methods on the labelled faces in the wild and YouTube face verification tasks.

Deep-learned faces: a survey

This paper first discusses the evolution of related network architectures, then a comparative analysis of loss functions, classification algorithms, and face datasets is given and a comparative study of state-of-the-art face recognition systems is presented.

Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition

  • Changxing DingD. Tao
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
A Trunk-Branch Ensemble CNN model (TBE-CNN), which extracts complementary information from holistic face images and patches cropped around facial components, achieves state-of-the-art performance on three popular video face databases: PaSC, COX Face, and YouTube Faces.

A joint loss function for deep face recognition

This paper proposes to learn an effective feature from face images by a joint loss function which combines the hard sample triplet (HST) and the absolute constraint triplets (ACT) loss, under the criteria that a maximum intra- class distance should be smaller than any inter-class distance.

Face recognition with compressed Fisher vector on multiscale convolutional features

A new framework called joint compressed Fisher vector (JCFV), which generate task-specific data representation by jointly encoding multiscale deep convolutional activations and calculating a re-weighted first-order statistics.

Unconstrained Face Verification Based on Monogenic Binary Pattern and Convolutional Neural Network

The developed MBP-CNN has robustness to variations of illumination, occlusion, pose, expression, texture and shape by combining Monogenic Binary Pattern and convolutional neural network.
...

References

SHOWING 1-10 OF 43 REFERENCES

Learning Face Representation from Scratch

A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF.

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.

Deep Learning Face Representation by Joint Identification-Verification

This paper shows that the face identification-verification task can be well solved with deep learning and using both face identification and verification signals as supervision, and the error rate has been significantly reduced.

Web-scale training for face identification

A link between the representation norm and the ability to discriminate in a target domain is found, which sheds lights on how deep convolutional networks represent faces.

Deeply learned face representations are sparse, selective, and robust

This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition that is learned with the identification-verification supervisory signal, and finds it is much more robust to occlusions, although occlusion patterns are not included in the training set.

Multi-Task Pose-Invariant Face Recognition

A novel face identification framework capable of handling the full range of pose variations within ±90° of yaw is proposed and consistently outperforms single-task-based baselines as well as state-of-the-art methods for the pose problem.

FaceNet: A unified embedding for face recognition and clustering

A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.

Face Search at Scale: 80 Million Gallery

A face search system which combines a fast search procedure, coupled with a state-of-the-art commercial off the shelf (COTS) matcher, in a cascaded framework that offers an excellent trade-off between accuracy and scalability on datasets consisting of millions of images.

Learning Discriminant Face Descriptor

This paper proposes a method to learn a discriminant face descriptor (DFD) in a data-driven way and applies it to the heterogeneous (cross-modality) face recognition problem and learns DFD in a coupled way to reduce the gap between features of heterogeneous face images to improve the performance of this challenging problem.

Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

Experimental results indicate that DCP outperforms the state-of-the-art local descriptors for both face identification and face verification tasks and the best performance is achieved on the challenging LFW and FRGC 2.0 databases by deploying MDML-DCPs in a simple recognition scheme.