A Two-Phase Weighted Collaborative Representation for 3D partial face recognition with single sample

Lei, Yinjie; Guo, Yulan; Hayat, Munawar; Bennamoun, Mohammed; Zhou, Xiaolei

doi:10.1016/j.patcog.2015.09.035

Cited by 90 publications

(33 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the four experiments under varying occlusions, the proposed method has significantly outperformed other methods in one type of occlusion, and match or close to the best results in three other cases. The overall recognition rate is 8.7%, 7.1%, and 2.1% higher than the methods from Colombo et al [4], Drira et al [8] and Lei et al [14], respectively. This has confirmed that our method can effectively handle partial occlusions.…”

Section: Comparative Evaluation On Bosphorus Databasementioning

confidence: 65%

“…The representation and the elastic Riemannian framework are robust to handle expressions, pose variations, missing parts and partial occlusions. Lei et al [9] explored an efficient 3D face recognition that used a set of local-feature descriptors called KMTS to represent a 3D face, then a TPWCRC framework was proposed to address the problem of 3D partial face recognition. In their method, only one training sample face per person was needed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D face recognition under partial occlusions using radial strings

Gao

Zhou

2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

3D face recognition with partial occlusions is a highly challenging problem. In this paper, we propose a novel radial string representation and matching approach to recognize 3D facial scans in the presence of partial occlusions. Here we encode 3D facial surfaces into an indexed collection of radial strings emanating from the nosetips and Dynamic Programming (DP) is then used to measure the similarity between two radial strings. In order to address the recognition problems with partial occlusions, a partial matching mechanism is established in our approach that effectively eliminates those occluded parts and finds the most discriminative parts during matching process. Preliminary experimental results on the Bosphorus database demonstrate that the proposed approach yields superior performance on partially occluded data.

show abstract

Section: Comparative Evaluation On Bosphorus Databasementioning

confidence: 65%

Section: Introductionmentioning

confidence: 99%

3D face recognition under partial occlusions using radial strings

Gao

Zhou

2016

2016 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Thus, 3D face recognition is an active topic in biometrics. The majority of existing approaches are based on hand-crafted features [10,11] or 3D Morphable Model (3DMM) fitting [12,13]. The low-level approaches based on hand-crafted features have explicable descriptiveness and are powerful enough to handle normal scales of data, but they usually depend on algorithmic operations with a high complexity.…”

Section: Related Workmentioning

confidence: 99%

3D Visual passcode: Speech-driven 3D facial dynamics for behaviometrics

Zhang

Fisher²

2019

Signal Processing

View full text Add to dashboard Cite

Face biometrics have achieved remarkable performance over the past decades, but unexpected spoofing of the static faces poses a threat to information security. There is an increasing demand for stable and discriminative biological modalities which are hard to be mimicked and deceived. Speech-driven 3D facial motion is a distinctive and measurable behavior-signature that is promising for biometrics. In this paper, we propose a novel 3D behaviometrics framework based on a "3D visual passcode" derived from speech-driven 3D facial dynamics. The 3D facial dynamics are jointly represented by 3D-keypoint-based measurements and 3D shape patch features, extracted from both static and speech-driven dynamic regions. An ensemble of subject-specific classifiers are then trained over selected discriminative features, which allows for a discriminant speech-driven 3D facial dynamics representation. We construct the first publicly available Speech-driven 3D Facial Motion dataset (S3DFM) that includes 2D-3D face video plus audio samples from 77 participants. The experimental results on the S3DFM show that the proposed pipeline achieves a face identification rate of 96.1%. Detailed discussions are presented, concerning anti-spoofing, head pose variation, video frame rate, and applicability cases. We also give comparison with other baselines on "deep" and "shallow" 2D face features.

show abstract

“…Local shape descriptors based methods extracted discrete facial features from facial data to construct the face recognition framework. The discrete facial features included point cloud set [13], 3D key points based [14][15][16][17], and local surface analysis [18][19][20]. The discrete facial features such as surface points and local geometric descriptors did not require complex preprocess for face cropping and high quality triangular meshes of 3D face.…”

Section: Previous Workmentioning

confidence: 99%

3D Face Recognition based on Local Conformal Parameterization and Iso-Geodesic Stripes Analysis

Zhao

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

3D face recognition is an important topic in the field of pattern recognition and computer graphic. We propose a novel approach for 3D face recognition using local conformal parameterization and iso-geodesic stripes. In our framework, the 3D facial surface is considered as a Riemannian 2-manifold. The surface is mapped into the 2D circle parameter domain using local conformal parameterization. In the parameter domain, the geometric features are extracted from the iso-geodesic stripes. Combining the relative position measure, Chain 2D Weighted Walkthroughs (C2DWW), the 3D face matching results can be obtained. The geometric features from iso-geodesic stripes in parameter domain are robust in terms of head poses, facial expressions, and some occlusions. In the experiments, our method achieves a high recognition accuracy of 3D facial data from the Texas3D and Bosphorus3D face database.

show abstract

A Two-Phase Weighted Collaborative Representation for 3D partial face recognition with single sample

Cited by 90 publications

References 69 publications

3D face recognition under partial occlusions using radial strings

3D face recognition under partial occlusions using radial strings

3D Visual passcode: Speech-driven 3D facial dynamics for behaviometrics

3D Face Recognition based on Local Conformal Parameterization and Iso-Geodesic Stripes Analysis

Contact Info

Product

Resources

About