Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition

Wu, Wanglong; Kan, Meina; Liu, Xin; Yang, Yi; Shan, Shiguang; Chen, Xilin

doi:10.1109/iccv.2017.407

Cited by 52 publications

(45 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent work Wu et al [39] propose a recursive spatial transformer (ReST) for the alignment-free face recognition. They also integrate the recognition network in an end-to-end optimization manner.…”

Section: Related Workmentioning

confidence: 99%

“…Despite of the recent academic/commercial progresses made in deep learning [34], [31], [30], [47], [41], [28], [18], [37], [20], [36], [14], [42], [43], [39], it is still hard to claim that face recognition has been solved in unconstrained settings. One of the remaining challenges for the in-the-wild recognition is facial geometric variations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GridFace: Face Rectification via Learning Local Homography Transformations

Zhou¹,

Cao²,

Sun³

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance. Our method rectifies the face by local homography transformations, which are estimated by a face rectification network. To encourage the image generation with canonical views, we apply a regularization based on the natural face distribution. We learn the rectification network and recognition network in an end-to-end manner. Extensive experiments show our method greatly reduces geometric variations, and gains significant improvements in unconstrained face recognition scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

GridFace: Face Rectification via Learning Local Homography Transformations

Zhou¹,

Cao²,

Sun³

2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

show abstract

“…Face analysis is one of the most studied areas in various research communities including Computer Vision (CV) and Affective Computing (AC). Cutting edge results are constantly obtained for various face-related analysis and recognition tasks including face detection [60,62,63], face recognition [55], expression recognition [26], valence-arousal estimation [24], action unit detection [57,26], face attribute recognition [30,12], age estimation [5,15,1], landmark detection [31,45] and face alignment [19]. However, in order to get the best performance, Our system, which we refer to here as Face-SSD, detects faces and smiles, recognises facial attributes, and predicts affect along the valence and arousal dimensions, in the wild.…”

Section: Introductionmentioning

confidence: 99%

Registration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild

Jang

Güneş

Patras

2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

In this paper, we present a novel single shot face-related task analysis method, called Face-SSD, for detecting faces and for performing various face-related (classification / regression) tasks including smile recognition, face attribute prediction and valence-arousal estimation in the wild. Face-SSD uses a Fully Convolutional Neural Network (FCNN) to detect multiple faces of different sizes and recognise / regress one or more face-related classes. Face-SSD has two parallel branches that share the same low-level filters, one branch dealing with face detection and the other one with face analysis tasks. The outputs of both branches are spatially aligned heatmaps that are produced in paralleltherefore Face-SSD does not require that face detection, facial region extraction, size normalisation, and facial region processing are performed in subsequent steps. Our contributions are threefold: 1) Face-SSD is the first network to perform face analysis without relying on pre-processing such as face detection and registration in advance -Face-SSD is a simple and a single FCNN architecture simultaneously performing face detection and face-related task analysis -those are conventionally treated as separate consecutive tasks; 2) Face-SSD is a generalised architecture that is applicable for various face analysis tasks without modifying the network structure -this is in contrast to designing task-specific architectures; and 3) Face-SSD achieves real-time performance (21 FPS) even when detecting multiple faces and recognising multiple classes in a given image (300 × 300). Experimental results show that Face-SSD achieves state-of-the-art performance in various face analysis tasks by reaching a recognition accuracy of 95.76% for smile detection, 90.29% for attribute prediction, and Root Mean Square (RMS) error of 0.44 and 0.39 for valence and arousal estimation. (Youngkyoon Jang) recent studies design specific architectures for each individual face analysis task. Although some works propose unified frameworks for handling multiple face-related tasks [56,3,35], several open issues remain yet to be explored:• Unconstrained conditions: Most of the existing approaches require a detected and normalised face input.• Scalability: Most methods design separate networks for different tasks. However, networks that are specifically designed to maximise the performance for certain tasks cannot be easily adapted to do other types of face analysis tasks.• Real-time performance: Existing methods do not achieve real-time performance because they require time-

show abstract

“…However, without any assistance, the SPO face recognition methods cannot achieve successful recognition in uncontrollable variations. Currently, some researches focused on contextual information and learning-based algorithms [23][24][25]. In [23], the contextaware local binary feature achieves better robustness than the local feature descriptor such as LDA.…”

Section: Introductionmentioning

confidence: 99%

“…In [23], the contextaware local binary feature achieves better robustness than the local feature descriptor such as LDA. The convolutional neural networks [24,25] were introduced for face recognition to show better performance than the SPO approaches if a suitable deep network with a large tagged database is learnt. However, the learning approaches, which need intensive computation for training and testing computation, may not be suitable for real-time applications in current handheld devices.…”

Section: Introductionmentioning

confidence: 99%

Multi-feature shape regression for face alignment

Yang

Chen

Chung

et al. 2018

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

For smart living applications, personal identification as well as behavior and emotion detection becomes more and more important in our daily life. For identity classification and facial expression detection, facial features extracted from face images are the most popular and low-cost information. The face shape in terms of landmarks estimated by a face alignment method can be used for many applications including virtual face animation and real face classification. In this paper, we propose a robust face alignment method based on the multi-feature shape regression (MSR), which is evolved from the explicit shape regression (ESR) proposed in Cao et al. (Int, Vis, 2014, 107:177-190, Comput). The proposed MSR face alignment method successfully utilizes color, gradient, and regional information to increase accuracy of landmark estimation. For face recognition algorithms, we further suggest a face warping algorithm, which can cooperate with any face alignment algorithm to adjust facial pose variations to improve their recognition performances. For performance evaluations, the proposed and the existing face alignment methods are compared on the face alignment database. Based on alignment-based face recognition concept, the face alignment methods with the proposed face warping method are tested on the face database. Simulation results verify that the proposed MSR face alignment method achieves better performances than the other existing face alignment methods.

show abstract

Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition

Cited by 52 publications

References 14 publications

GridFace: Face Rectification via Learning Local Homography Transformations

GridFace: Face Rectification via Learning Local Homography Transformations

Registration-free Face-SSD: Single shot analysis of smiles, facial attributes, and affect in the wild

Multi-feature shape regression for face alignment

Contact Info

Product

Resources

About