A Survey on 3D Modeling of Human Faces for Face Recognition

Huq, S.; Abidi, B.; Kong, Seong G.; Abidi, Mongi A.

doi:10.1007/978-1-4020-6182-0_2

Cited by 7 publications

(5 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Günther et al [12] have found that these traditional face recognition algorithms are not designed to and, therefore, do not perform very well on images with uncontrolled factors such as facial expression, non-frontal illumination, partial occlusions of the face, or non-frontal face pose, which occur in modern face recognition datasets [15,18]. While different strategies have been proposed to improve the performance of traditional algorithms across pose, e.g., using face frontalization techniques [14] or 3D modeling [16], the introduction of deep convolutional neural networks (DC-NNs) for face recognition [36,24] has overcome the pose issue to a significant extent. For example, deep neural net-works have outperformed traditional methods by such a wide margin on the labeled faces in the wild (LFW) benchmark [15] that this once challenging benchmark is now considered quite easy, at least under the conventional verification protocol.…”

Section: Introductionmentioning

confidence: 99%

Toward Open-Set Face Recognition

Günther

Cruz

Rudd

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Much research has been conducted on both face identification and face verification, with greater focus on the latter. Research on face identification has mostly focused on using closed-set protocols, which assume that all probe images used in evaluation contain identities of subjects that are enrolled in the gallery. Real systems, however, where only a fraction of probe sample identities are enrolled in the gallery, cannot make this closed-set assumption. Instead, they must assume an open set of probe samples and be able to reject/ignore those that correspond to unknown identities. In this paper, we address the widespread misconception that thresholding verification-like scores is a good way to solve the open-set face identification problem, by formulating an open-set face identification protocol and evaluating different strategies for assessing similarity. Our open-set identification protocol is based on the canonical labeled faces in the wild (LFW) dataset. Additionally to the known identities, we introduce the concepts of known unknowns (known, but uninteresting persons) and unknown unknowns (people never seen before) to the biometric community. We compare three algorithms for assessing similarity in a deep feature space under an open-set protocol: thresholded verificationlike scores, linear discriminant analysis (LDA) scores, and an extreme value machine (EVM) probabilities. Our findings suggest that thresholding EVM probabilities, which are open-set by design, outperforms thresholding verificationlike scores.

show abstract

Section: Introductionmentioning

confidence: 99%

Toward Open-Set Face Recognition

Günther

Cruz

Rudd

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…At the algorithmic level, the techniques vary depending on the modes of model representation (or registration) [2], feature extraction [3] and matching [4]. A good set of survey papers [5] provide varied systems on generic 3DFR. These cover a range of techniques starting from imaging, representation, matching, both grey scale as well as colour images.…”

Section: Review Of Current Positionmentioning

confidence: 99%

3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

Ramalingam

2013

2013 IEEE International Conference on Systems, Man, and Cybernetics

View full text Add to dashboard Cite

In this paper, the author presents a work on i) range data and ii) stereo-vision system based disparity map profiling that are used as signatures for 3D face recognition. The signatures capture the intensity variations along a line at sample points on a face in any particular direction. The directional signatures and some of their combinations are compared to study the variability in recognition performances. Two 3D face image datasets namely, a local student database captured with a stereo vision system and the FRGC v1 range dataset are used for performance evaluation.

show abstract

“…Passive techniques, like stereo vision, shape-from-shading or shape-from-motion usually lack adequate accuracy for 3D face modelling [45]. Spatial resolution for these techniques are in the mm range.…”

Section: D Data Acquisitionmentioning

confidence: 99%

“…With current available devices, active systems based on triangulation offer higher accuracy compared to systems based on time-of-flight [45]. Regardless of the data acquisition technique used, the scans have to be processed to remove scanning artefacts like holes and spikes.…”

Section: D Data Acquisitionmentioning

confidence: 99%

Inverse Rendering of Faces with a 3D Morphable Model

Aldrian

Smith

2013

IEEE Trans. Pattern Anal. Mach. Intell.

179

160

View full text Add to dashboard Cite

In this thesis, we present a complete framework to inverse render faces with a 3D Morphable Model. By decomposing the image formation process into a geometric and photometric part, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a globally optimal solution can be found. We start by recovering 3D shape using a novel algorithm which incorporates generalisation errors of the model obtained from empirical measurements. The algorithm is extended so it can efficiently deal with mixture distributions. We then describe three methods to recover facial texture, and for the second and third, diffuse lighting, specular reflectance and camera properties from a single image. These methods make increasingly weak assumptions and can all be solved in a linear fashion. We further modify our framework so it accounts for global illumination effects. This is achieved by incorporating statistical models for ambient occlusion and bent normals into the image formation model. We show that solving for ambient occlusion and bent normal parameters as part of the fitting process improves the accuracy of the estimated texture map and illumination environment. We present results on challenging data, rendered under complex natural illumination with both specular reflectance and occlusion of the illumination environment. We evaluate our findings on publicly available datasets, where we are able to obtain state-ofthe-art results. Finally, we present a practical method to synthesise a larger population from a small training-set and show how the new instances can be used to build a flexible PCA model.

show abstract

A Survey on 3D Modeling of Human Faces for Face Recognition

Cited by 7 publications

References 106 publications

Toward Open-Set Face Recognition

Toward Open-Set Face Recognition

3D Face Recognition: Feature Extraction Based on Directional Signatures from Range Data and Disparity Maps

Inverse Rendering of Faces with a 3D Morphable Model

Contact Info

Product

Resources

About