Morphable Displacement Field Based Image Matching for Face Recognition across Pose

Li, Shaoxin; Liu, Xin; Chai, Xiujuan; Zhang, Haihong; Lao, Shihong; Shan, Shiguang

doi:10.1007/978-3-642-33718-5_8

Cited by 71 publications

(55 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These images were captured in four sessions during different periods. Like the previous methods [3,18,17], we evaluate our algorithm on a subset of the MultiPIE database, where each identity has images from all the four sections under seven poses from yaw angles −45…”

Section: Methodsmentioning

confidence: 99%

“…The existing works conduct experiments on MultiPIE with three different settings: Setting-I was introduced in [3,18,34]; Setting-II and Setting-III were introduced in [17]. We describe these settings below.…”

Section: Face Recognitionmentioning

confidence: 99%

“…Many existing works have been proposed to account for such variations. The pose-invariant methods can be generally separated into two categories: 2D-based [17,5,23] and 3D-based [18,3]. In the first category, poses are either handled by 2D image matching or by encoding a test image using some bases or exemplars.…”

Section: Introductionmentioning

confidence: 99%

“…Such methods make it possible to synthesize any view of the probe face, which makes them generally more robust to pose variation. For instance, Li et al [18] first generated a virtual view for the probe face by using a set of 3D displacement fields sampled from a 3D face database, and then matched the synthesized face with the gallery faces. Similarly, Asthana et al [3] matched the 3D model to a 2D image using the view-based active appearance model.…”

Section: Introductionmentioning

confidence: 99%

“…The above methods have certain limitations. For example, capturing 3D data requires additional cost and resources [18]. Inferring 3D models from 2D data is an illposed problem [23].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning Identity-Preserving Face Space

Zhu

Luo

Wang

et al. 2013

2013 IEEE International Conference on Computer Vision

279

198

View full text Add to dashboard Cite

Face recognition with large pose and illumination variations is a challenging problem in computer vision. This paper addresses this challenge by proposing a new learningbased face representation: the face identity-preserving (FIP) features. Unlike conventional face descriptors, the FIP features can significantly reduce intra-identity variances, while maintaining discriminativeness between identities. Moreover, the FIP features extracted from an image under any pose and illumination can be used to reconstruct its face image in the canonical view. This property makes it possible to improve the performance of traditional descriptors, such as LBP [2] and Gabor [31], which can be extracted from our reconstructed images in the canonical view to eliminate variations. In order to learn the FIP features, we carefully design a deep network that combines the feature extraction layers and the reconstruction layer. The former encodes a face image into the FIP features, while the latter transforms them to an image in the canonical view. Extensive experiments on the large MultiPIE face database [7] demonstrate that it significantly outperforms the state-of-the-art face recognition methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Face Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The above methods have certain limitations. For example, capturing 3D data requires additional cost and resources [18]. Inferring 3D models from 2D data is an illposed problem [23].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Identity-Preserving Face Space

Zhu

Luo

Wang

et al. 2013

2013 IEEE International Conference on Computer Vision

279

198

View full text Add to dashboard Cite

show abstract

Human identification in health care systems using mobile edge computing

Choi

2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Mobile edge computing (MEC) is a new technology that provides an IT service environment and cloud-computing resource at the edge of the mobile network, aiming to improve the user experience by reducing latency and delivering highly efficient services. A mobile health care system is a typical case of MEC. Recent advances in mobile health technology enable us to automatically record the states and behaviors of patients in hospitals by identifying their faces. Instead of using a centralized server or cloud to process these heavy loading analyses, MEC analyzes the patients' behavior locally in their rooms to enable quick response to their accidents and reduce the storage size of large-scale patient information. By using MEC, only one frontal face for each patient is available in the gallery to reduce the local computational power. Although a patient's face can be captured from any other pose, doing so challenges the face-identification algorithm. Several studies have been published to solve this problem, but most of them rely on pose estimation and landmark detection. In this paper, we propose a deeper convolutional neural network to extract the pose-invariant face features and synthesize the virtual poses simultaneously, aiming to develop a landmark-free and pose-estimation-free frontal-face synthesis system. The deeper network was divided into multiple overlapped local networks, each one trained to synthesize a small pose change, such as one larger than 45 • to30 •. The local networks were jointly trained to synthesize the frontal face from a nonfrontal pose in a progressive manner. By stacking multiple local networks, we were able to extract more robust pose-invariant features, to generate multiple virtual poses before the frontal face was synthesized. The pose-invariant features and virtual poses were incorporated to identify the face across poses. The proposed method was evaluated on the CAS-PEAL dataset with 16 layers and fine-tuned on the FERET dataset with 12 layers. The experimental results showed our network achieved impressive performance for pose-unconstrained face recognition, which can be applied for human identification in healthcare systems using MEC.

show abstract

Face Recognition Using a Unified 3D Morphable Model

Yan

Chan

et al. 2016

Computer Vision – ECCV 2016

View full text Add to dashboard Cite

Abstract. We address the problem of 3D-assisted 2D face recognition in scenarios when the input image is subject to degradations or exhibits intra-personal variations not captured by the 3D model. The proposed solution involves a novel approach to learn a subspace spanned by perturbations caused by the missing modes of variation and image degradations, using 3D face data reconstructed from 2D images rather than 3D capture. This is accomplished by modelling the difference in the texture map of the 3D aligned input and reference images. A training set of these texture maps then defines a perturbation space which can be represented using PCA bases. Assuming that the image perturbation subspace is orthogonal to the 3D face model space, then these additive components can be recovered from an unseen input image, resulting in an improved fit of the 3D face model. The linearity of the model leads to efficient fitting. Experiments show that our method achieves very competitive face recognition performance on Multi-PIE and AR databases. We also present baseline face recognition results on a new data set exhibiting combined pose and illumination variations as well as occlusion.

show abstract

Morphable Displacement Field Based Image Matching for Face Recognition across Pose

Cited by 71 publications

References 16 publications

Deep Learning Identity-Preserving Face Space

Deep Learning Identity-Preserving Face Space

Human identification in health care systems using mobile edge computing

Face Recognition Using a Unified 3D Morphable Model

Contact Info

Product

Resources

About