Conformal Mapping of a 3D Face Representation onto a 2D Image for CNN Based Face Recognition

Kittler, Josef; Koppen, Paul; Kopp, Philipp; Huber, Patrik; Rätsch, Matthias

doi:10.1109/icb2018.2018.00029

Cited by 17 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a generic representation of the face texture is created with an algorithm for rectangular texture maps that finds a projection from the 3D vertices to a 2D plane that preserves the geodesic distance between the mesh vertices. We follow the method for performing these steps described in (Kittler et al, 2018). As advocated in (Kittler et al, 2018), we use a conformal Laplacian Eigenmap where the boundary vertices are constrained to a square, as shown in Figure 2, calling it square texture map.…”

Section: Methodsologymentioning

confidence: 99%

“…We follow the method for performing these steps described in (Kittler et al, 2018). As advocated in (Kittler et al, 2018), we use a conformal Laplacian Eigenmap where the boundary vertices are constrained to a square, as shown in Figure 2, calling it square texture map. The texture map contains the remapped texture of the original 2D image, preserving all details.…”

Section: Methodsologymentioning

confidence: 99%

“…There are some existing face recognition systems (Masi et al, 2016;Kittler et al, 2018;Koppen et al, 2018) which take 3D shape of face into account and synthesise frontal faces by using 3D information. Kittler et al (Kittler et al, 2018) have combined 3D shape and texture information for face recognition and have shown that the system benefits more from texture than from shape. Motivated by their work, in this paper we investigate different approaches to improve a face recognition system based on texture maps.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Texture-based 3D Face Recognition using Deep Neural Networks for Unconstrained Human-machine Interaction

Danner

Raetsch

Huber

et al. 2020

Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

Self Cite

View full text Add to dashboard Cite

3D assisted 2D face recognition involves the process of reconstructing 3D faces from 2D images and solving the problem of face recognition in 3D. To facilitate the use of deep neural networks, a 3D face, normally represented as a 3D mesh of vertices and its corresponding surface texture, is remapped to image-like square isomaps by a conformal mapping. Based on previous work, we assume that face recognition benefits more from texture. In this work, we focus on the surface texture and its discriminatory information content for recognition purposes. Our approach is to prepare a 3D mesh, the corresponding surface texture and the original 2D image as triple input for the recognition network, to show that 3D data is useful for face recognition. Texture enhancement methods to control the texture fusion process are introduced and we adapt data augmentation methods. Our results show that texture-map-based face recognition can not only compete with state-of-the-art systems under the same preconditions but also outperforms standard 2D methods from recent years.

show abstract

Section: Methodsologymentioning

confidence: 99%

Section: Methodsologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Texture-based 3D Face Recognition using Deep Neural Networks for Unconstrained Human-machine Interaction

Danner

Raetsch

Huber

et al. 2020

Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, we also mention the works of Zhu et al [6] and Sinha et al [7]. In [6], similarly to [5], a 3DMM is fit to a 2D image, but for face image frontalization purposes. The face alignment method employs a cascaded CNN to handle the self-occlusions.…”

Section: Introductionmentioning

confidence: 99%

Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection

Taha

Hayat

Hatzinakos

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

This paper proposes an approach to learn generic multi-modal mesh surface representations using a novel scheme for fusing texture and geometric data. Our approach defines an inverse mapping between different geometric descriptors computed on the mesh surface or its down-sampled version, and the corresponding 2D texture image of the mesh, allowing the construction of fused geometrically augmented images (FGAI). This new fused modality enables us to learn feature representations from 3D data in a highly efficient manner by simply employing standard convolutional neural networks in a transfer-learning mode. In contrast to existing methods, the proposed approach is both computationally and memory efficient, preserves intrinsic geometric information and learns highly discriminative feature representation by effectively fusing shape and texture information at data level. The efficacy of our approach is demonstrated for the tasks of facial action unit detection and expression classification. The extensive experiments conducted on the Bosphorus and BU-4DFE datasets, show that our method produces a significant boost in the performance when compared to state-of-the-art solutions.

show abstract

“…On the other hand, face verification aims to identify a face template against the claimed identity [8]. The challenging problems of face recognition include Pose, Expression, and Illumination (PIE) variations [9]. Despite the great success made over the past, robust face recognition using 2D intensity images is still a significant challenging problem in the presence of PIE variations [10].…”

Section: Introductionmentioning

confidence: 99%

Deeply Learned Pose Invariant Image Analysis with Applications in 3D Face Recognition

Ratyal

Taj

Sajid

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Face recognition aims to establish the identity of a person based on facial characteristics and is a challenging problem due to complex nature of the facial manifold. A wide range of face recognition applications are based on classification techniques and a class label is assigned to the test image that belongs to the unknown class. In this paper, a pose invariant deeply learned multiview 3D face recognition approach is proposed and aims to address two problems: face alignment and face recognition through identification and verification setups. The proposed alignment algorithm is capable of handling frontal as well as profile face images. It employs a nose tip heuristic based pose learning approach to estimate acquisition pose of the face followed by coarse to fine nose tip alignment using L2 norm minimization. The whole face is then aligned through transformation using knowledge learned from nose tip alignment. Inspired by the intrinsic facial symmetry of the Left Half Face (LHF) and Right Half Face (RHF), Deeply learned (d) Multi-View Average Half Face (d-MVAHF) features are employed for face identification using deep convolutional neural network (dCNN). For face verification d-MVAHF-Support Vector Machine (d-MVAHF-SVM) approach is employed. The performance of the proposed methodology is demonstrated through extensive experiments performed on four databases: GavabDB, Bosphorus, UMB-DB, and FRGC v2.0. The results show that the proposed approach yields superior performance as compared to existing state-of-the-art methods.

show abstract

Conformal Mapping of a 3D Face Representation onto a 2D Image for CNN Based Face Recognition

Cited by 17 publications

References 20 publications

Texture-based 3D Face Recognition using Deep Neural Networks for Unconstrained Human-machine Interaction

Texture-based 3D Face Recognition using Deep Neural Networks for Unconstrained Human-machine Interaction

Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection

Deeply Learned Pose Invariant Image Analysis with Applications in 3D Face Recognition

Contact Info

Product

Resources

About