Deep transformation learning for face recognition in the unconstrained scene

Chen, Guanhao; Shao, Yi; Tang, Chaowei; Jin, Zhuoyi; Zhang, Jinkun

doi:10.1007/s00138-018-0907-1

Cited by 18 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LFW(Accuracy ± Std) DeepFace [23] 95.92% ± 0.29% COTS matcher [24] 98.2% ± 0.6% DeepID-2+ [25] 98.70% ± 0.15% Chen et al [26] 99.16% ± 0.31% PTFRM_PYR 99.43% ± 0.16% From Table 1, we can see that the average accuracy of the algorithm in this study is 99.43%, and the deviation is ±0.16%, which is better than the comparison algorithm. The results show that the network of the algorithm in this study is very stable and has a strong generalization ability.…”

Section: Algorithmsmentioning

confidence: 99%

“…DeepFace [23] 95.92% ± 0.29% COTS matcher [24] 98.2% ± 0.6% DeepID-2+ [25] 98.70% ± 0.15% Chen et al [26] 99.16% ± 0.31% PTFRM_PYR 99.43% ± 0.16%…”

Section: Algorithms Lfw (Accuracy ± Std)mentioning

confidence: 99%

“…Deep-Multi-Pose [30] 84.60% ± -92.70% ± -Multi-task CNN [31] 85.80% ± 1.40% 93.80% ± 0.9% PAMs [8] 86.20% ± 1.3 0% 94.30% ± 0.9% DR-GAN [13] 91.0% ± 1.5% 95.6% ± 1.1% Chen et al [26] 87.30% ± -93.10% ± -PTFRM_Y 91.62% ± 0.62% 93.87% ± 0.57% PTFRM_PYR 94.33% ± 0.84% 97.06% ± 0.64%…”

Section: Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene

et al. 2020

Self Cite

View full text Add to dashboard Cite

At present, deep learning drives the rapid development of face recognition. However, in the unconstrained scenario, the change of facial posture has a great impact on face recognition. Moreover, the current model still has some shortcomings in accuracy and robustness. The existing research has formulated two methods to solve the above problems. One method is to model and train each pose separately. Then, a fusion decision will be made. The other method is to make “frontal” faces on the image or feature level and transform them into “frontal” face recognition. Based on the second idea, we propose a profile to the frontal revise mapping (PTFRM) module. This module realizes the revision of arbitrary poses on the feature level and transforms the multi-pose features into an approximate frontal representation to enhance the recognition ability of the existing recognition models. Finally, we evaluate the PTFRM on unconstrained face validation benchmark datasets such as Labeled Faces in the Wild (LFW), Celebrities in Frontal Profile (CFP), and IARPA Janus Benchmark A(IJB-A). Results show that the chosen method for this study achieves good performance.

show abstract

Section: Algorithmsmentioning

confidence: 99%

“…DeepFace [23] 95.92% ± 0.29% COTS matcher [24] 98.2% ± 0.6% DeepID-2+ [25] 98.70% ± 0.15% Chen et al [26] 99.16% ± 0.31% PTFRM_PYR 99.43% ± 0.16%…”

Section: Algorithms Lfw (Accuracy ± Std)mentioning

confidence: 99%

See 1 more Smart Citation

Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, with the improvement of computer computing performance and the graphics processors, deep model learning becomes possible for common researchers. Now it has been gradually applied in image classification [5]- [7] , expression recognition [8]- [10] , speech recognition [11]- [14] , etc.…”

Section: A Ram In Deep Learningmentioning

confidence: 99%

An Efficient and Accurate DDPG-Based Recurrent Attention Model for Object Localization

Ke¹

2020

IEEE Access

View full text Add to dashboard Cite

Using image processing algorithm to localize objects, which lack specific patterns and local features, has always been the research focus in industrial production. Compared with the traditional image processing algorithm, RAM (Recurrent Attention Model) in deep learning not only shows advantages in positioning accuracy and stability, but also has good adaptability in situations such as occlusion. However, RAM contains policy gradient (PG) algorithm, which is unstable in training process and has low convergence efficiency. To overcome this shortcoming, in order to improve the learning efficiency and stability of RAM, this paper proposes DDPG-based RAM. In addition, current random sampling algorithm in DDPG (Deep Deterministic Policy Gradient) does not make full use of the information contained in samples. Some samples are repeatedly learned, which slows down the convergence rate of the neural network model, and even causes the model to converge to the local optimal solution. To solve the above problems, a prioritized experience replay algorithm based on Gaussian sampling method is proposed. By constructing the localization and grasping simulation environment in V-rep, it is shown that compared with the traditional image algorithm, the proposed model algorithm in this paper has a greater improvement in localization accuracy, stability and model convergence speed.

show abstract

“…Different approaches are proposed in solving the problem with this method. In the constrained scenes, such as airport scanners or ATM cash withdrawal, a frontal image is captured, which is quite straightforward, and it is different from the context in which the scene is not constrained [9].…”

Section: Research Motivationsmentioning

confidence: 99%

Comparison of Random Subspace and Voting Ensemble Machine Learning Methods for Face Recognition

2018

View full text Add to dashboard Cite

Biometry based authentication and recognition have attracted greater attention due to numerous applications for security-conscious societies, since biometrics brings accurate and consistent identification. Face biometry possesses the merits of low intrusiveness and high precision. Despite the presence of several biometric methods, like iris scan, fingerprints, and hand geometry, the most effective and broadly utilized method is face recognition, because it is reasonable, natural, and non-intrusive. Face recognition is a part of the pattern recognition that is applied for identifying or authenticating a person that is extracted from a digital image or a video automatically. Moreover, current innovations in big data analysis, cloud computing, social networks, and machine learning have allowed for a straightforward understanding of how different challenging issues in face recognition might be solved. Effective face recognition in the enormous data concept is a crucial and challenging task. This study develops an intelligent face recognition framework that recognizes faces through efficient ensemble learning techniques, which are Random Subspace and Voting, in order to improve the performance of biometric systems. Furthermore, several methods including skin color detection, histogram feature extraction, and ensemble learner-based face recognition are presented. The proposed framework, which has a symmetric structure, is found to have high potential for biometrics. Hence, the proposed framework utilizing histogram feature extraction with Random Subspace and Voting ensemble learners have presented their superiority over two different databases as compared with state-of-art face recognition. This proposed method has reached an accuracy of 99.25% with random forest, combined with both ensemble learners on the FERET face database.

show abstract

Deep transformation learning for face recognition in the unconstrained scene

Cited by 18 publications

References 26 publications

Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene

Multi-Pose Face Recognition Based on Deep Learning in Unconstrained Scene

An Efficient and Accurate DDPG-Based Recurrent Attention Model for Object Localization

Comparison of Random Subspace and Voting Ensemble Machine Learning Methods for Face Recognition

Contact Info

Product

Resources

About