Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD

@article{JuefeiXu2014HallucinatingTF,
  title={Hallucinating the Full Face from the Periocular Region via Dimensionally Weighted K-SVD},
  author={Felix Juefei-Xu and D. K. Pal and M. Savvides},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2014},
  pages={1-8}
}
Identifying a suspect wearing a mask (where only the suspect's periocular region is visible) is one of the toughest real-world challenges in biometrics that exist. In this paper, we present a practical method to hallucinate the full frontal face given only the periocular region of a face. This is an important problem faced in many law-enforcement applications on almost a daily basis. In such real-world situations, we only have access to the periocular region of a person's face. Unfortunately… Expand
Unconstrained Periocular Face Recognition: From Reconstructive Dictionary Learning to Generative Deep Learning and Beyond
TLDR
It will be demonstrated that face matching using the periocular region directly is more robust than the full face in terms of age-tolerant face recognition, expression-tolerance face recognition; as well as contains more cues for determining the gender information of a subject. Expand
NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction
TLDR
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
Spartans: Single-Sample Periocular-Based Alignment-Robust Recognition Technique Applied to Non-Frontal Scenarios
TLDR
This paper investigates a single-sample periocular-based alignment-robust face recognition technique that is pose-tolerant under unconstrained face matching scenarios and solidly outperformed the state-of-the-art algorithms under four evaluation protocols. Expand
Learning to Invert Local Binary Patterns
TLDR
The proposed inversion of the local binary patterns (LBP) descriptor yields face reconstruction with high fidelity and also enables secure application with a unique encryption key and is shown to be effective on the FRGC ver 2.0 database. Expand
Fastfood dictionary learning for periocular-based full face hallucination
  • Felix Juefei-Xu, M. Savvides
  • Computer Science
  • 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)
  • 2016
TLDR
This work has shown that the approximated kernel expansion using Fastfood transform for joint dictionary learning yields much better results than its image space counterparts, enabling applications that require reconstructive dictionaries such as cross-domain reconstruction, image super-resolution, missing data recovery, etc. Expand
Periocular biometrics: databases, algorithms and directions
TLDR
A review of the state of the art in periocular biometric research is presented, providing an insight of the most relevant issues and giving a thorough coverage of the existing literature. Expand
Investigating the feasibility of image-based nose biometrics
TLDR
This study extracts discriminative nasal features using Kernel Class-Dependence Feature Analysis (KCFA) based on Optimal Trade-off Synthetic Discriminant Function (OTSDF) filters and finds that the between-subject discriminability in nasal features is comparable to that found in facial features. Expand
Single face image super-resolution via solo dictionary learning
TLDR
The core idea of the proposed method is to recast the super-resolution task as a missing pixel problem, where the low-resolution image is considered as its high-resolution counterpart with many pixels missing in a structured manner. Expand
Subspace-Based Discrete Transform Encoded Local Binary Patterns Representations for Robust Periocular Matching on NIST’s Face Recognition Grand Challenge
TLDR
The proposed approach using only the periocular region is almost as good as full face with only 2.5% reduction in verification rate at 0.1% false accept rate, yet it gains tolerance to expression, occlusion, and capability of matching partial faces in crowds. Expand
A survey on periocular biometrics research
TLDR
This work is expected to provide an insight of the most relevant issues in periocular biometrics, giving a comprehensive coverage of the existing literature and current state of the art. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 20 REFERENCES
Periocular region appearance cues for biometric identification
TLDR
It is demonstrated that recognition performance of the periocular region images is comparable to that of face. Expand
Unconstrained periocular biometric acquisition and recognition using COTS PTZ camera for uncooperative and non-cooperative subjects
We propose an acquisition and recognition system based only on periocular biometric using the COTS PTZ camera to tackle the difficulty that the full face recognition approach has encountered inExpand
Robust local binary pattern feature sets for periocular biometric identification
TLDR
Several filter-based techniques and local feature extraction methods are explored in this study, where an increase of 15% verification performance at 0.1% false accept rate (FAR) is shown compared to raw pixels with the proposed Local Walsh-Transform Binary Pattern encoding. Expand
Subspace-Based Discrete Transform Encoded Local Binary Patterns Representations for Robust Periocular Matching on NIST’s Face Recognition Grand Challenge
TLDR
The proposed approach using only the periocular region is almost as good as full face with only 2.5% reduction in verification rate at 0.1% false accept rate, yet it gains tolerance to expression, occlusion, and capability of matching partial faces in crowds. Expand
Investigating age invariant face recognition based on periocular biometrics
TLDR
This paper uses unsupervised discriminant projection (UDP) to build subspaces on WLBP featured periocular images and gain 100% rank-1 identification rate and 98% verification rate at 0.1% false accept rate on the entire FG-NET database. Expand
Periocular Biometrics in the Visible Spectrum
TLDR
The feasibility of using the periocular region as a biometric trait is studied, including the effectiveness of incorporating the eyebrows, and use of side information (left or right) in matching. Expand
On the Fusion of Periocular and Iris Biometrics in Non-ideal Imagery
TLDR
Experiments on the images extracted from the Near Infra-Red (NIR) face videos of the Multi Biometric Grand Challenge (MBGC) dataset demonstrate that valuable information is contained in the periocular region and it can be fused with the iris texture to improve the overall identification accuracy in non-ideal situations. Expand
Identifying useful features for recognition in near-infrared periocular images
TLDR
Eyelashes, tear ducts, shape of the eye, and eyelids were used most frequently in determining whether two images were from the same person, and the outer corner of theEye and the shape ofThe eye were used a higher proportion of the time for incorrect responses than they were for correct responses, suggesting that those two features are not as useful. Expand
Can your eyebrows tell me who you are?
  • Felix Juefei-Xu, M. Savvides
  • Computer Science
  • 2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS)
  • 2011
TLDR
This paper is the first to evaluate the recognition performance of eyebrow on such a big database and compare to the performance of full face and uses multiple discrete transform encoded features to capture the local information of eyebrow as well as full face. Expand
Periocular biometrics in the visible spectrum: A feasibility study
  • U. Park, A. Ross, Anil K. Jain
  • Computer Science
  • 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems
  • 2009
TLDR
The feasibility of using periocular images of an individual as a biometric trait using texture and point operators resulting in a feature set that can be used for matching is studied. Expand
...
1
2
...