FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion

Fu, Youhua; Ruan, Qiuqi; Luo, Ziyan; Jin, Yi; An, Gaoyun; Wan, Jun

doi:10.1016/j.sigpro.2019.03.015

Cited by 25 publications

(14 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[12,17,47] are three earlier studies for 3D facial expression recognition, and their experiments were repeated only for 10 times, which made the performance stability unguaranteed. When such an experimental protocol is utilised, the average recognition accuracy of our proposed method (OTDFPFER) achieves 95.49% that is better than that in ref [7,9,12,17,26,47]. As reproduced by Gong et al [10], the accuracies observed in [12,17,47] were found to be degraded greatly by adopting Setups I and II regarded as the stable experimental protocols.…”

Section: Comparison With Other Tensor Methodsmentioning

confidence: 65%

“…Table 8 indicates the comparison results in terms of data, features, classifiers, and accuracies, in which [14] achieves the lowest accuracy. From Table 8, it is obviously observed that the accuracies of OTDFPFER and the method [26] are very similar (75.97 % vs. 75.93 % ). It can be seen that expressions are difficult to be recognized for the Bosphorus database without expression intensity.…”

Section: Experiments Resultsmentioning

confidence: 96%

“…Three state‐of‐the‐art methods (i.e., [14, 26, 48]) are compared with our proposed OTDFPFER approach by utilising Setup III, aiming to validate the efficiency of OTDFPFER on the Bosphorus database. Table 8 indicates the comparison results in terms of data, features, classifiers, and accuracies, in which [14] achieves the lowest accuracy.…”

Section: Experiments Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Orthogonal tucker decomposition using factor priors for 2D+3D facial expression recognition

Ruan

Luo

et al. 2021

IET Biometrics

Self Cite

View full text Add to dashboard Cite

In this article, an effective approach is proposed to recognise the 2D+3D facial expression automatically based on orthogonal Tucker decomposition using factor priors (OTDFPFER). As a powerful technique, Tucker decomposition on the basis of the low rank approximation is often used to extract the useful information from the constructed 4D tensor composed of 3D face scans and 2D images aiming to maintain correlations and their structural information. Finding a set of projected factor matrices is our ultimate goal. During the 4D tensor modelling process, high similarities among samples will emerge because of the information missed partially. Based on the tensor orthogonal Tucker decomposition, the involved core tensor with the structured sparsity, and a graph regularisation term via the graph Laplacian matrix together with the fourth factor matrix are employed for better characterisation of the generated similarities and for keeping the consistency of low dimensional space. To recover the missing information, a framework for tensor completion (TC) will be embedded naturally. Finally, an alternating direction method coupled with the majorisation-minimisation scheme is designed to solve the resulting tensor completion problem. The numerical experiments are conducted on the Bosphorus and the BU-3DFE databases with promising recognition accuracies.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Comparison With Other Tensor Methodsmentioning

confidence: 65%

Section: Experiments Resultsmentioning

confidence: 96%

Section: Experiments Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Orthogonal tucker decomposition using factor priors for 2D+3D facial expression recognition

Ruan

Luo

et al. 2021

IET Biometrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In MFTNPE method, multi-feature tensor can maintain the structure of various features and allow us to investigate tensor features along every mode. Compared with tensor based method [42], our proposed MFTNPE method can extract discriminative tensor features, and can achieve the better performance by 0.42% recognition rate higher than in [42]. An unstable experimental proposal is utilized in method [43], where only 20 subjects are considered.…”

Section: ) Comparison With Other 3d Fer Methodsmentioning

confidence: 99%

Multi-Feature Tensor Neighborhood Preserving Embedding for 3D Facial Expression Recognition

Jiang

Ruan

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

To investigate an effective representation model for 3D facial expression recognition, this paper proposes a multi-feature tensor neighborhood preserving embedding (MFTNPE) method, which seeks various attribute features from raw textured shape scan models of 3D facial expression to construct a multi-feature tensor model. With MFTNPE method, we can project the model into a tensor subspace, explore the interactions and correlations among multimodal data and then extract discriminative low-dimensional tensor features for 3D facial expression recognition. In the study, we first introduce a tensor model based on multi-feature integration for 3D facial expression recognition. Via exploring the textural and geometric features of 3D facial expression data, an original multi-feature tensor model is constructed by stacking various attribute maps orderly. Second, we utilize the tensor completion approach as the scheme of data preprocessing to correct the original multi-feature tensor model. Due to the presence of imperfect data in the projected attribute maps, the tensor completion can predict the missing data in tensor by the trace norm of multi-feature tensor model along each mode. Third, we redefine a weighted matrix for use in the orthogonal-based tensor neighborhood preserving embedding algorithm. In the weighted matrix, the class information is used to guarantee the correct neighborhood relationships for multi-feature tensor samples. This effectively avoids the disturbances and confusions between similar samples while preserving spatial structure and inter-class information. Finally, we conduct extensive experiments on two 3D facial expression recognition datasets. The experimental results show that the proposed method has much better efficiency and performance compared with the state-of-the-art methods.INDEX TERMS 3D facial expression recognition, multi-feature, tensor decomposition, tensor representation, tensor neighborhood preserving embedding.

show abstract

“…Recent surveys [2,3] detail the research into FER over past decades. Deep CNNs have recently achieved good FER results [4,5,6,7,8,9,10,11,12,1,13,14,15,16,17,18,19,20], but they may also learn identity-related features that are irrelevant to expression and suffer from high intra-class variations and inter-class similarities, leading to a drop in FER performance on unseen subjects. Wen et al [21] introduced a center loss for face recognition to reduce intra-class variations, without explicitly considering inter-class similarity.…”

Section: Related Workmentioning

confidence: 99%

Identity-Free Facial Expression Recognition Using Conditional Generative Adversarial Network

Cai¹,

Meng²,

Khan

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

A novel Identity-Free conditional Generative Adversarial Network (IF-GAN) was proposed for Facial Expression Recognition (FER) to explicitly reduce high inter-subject variations caused by identity-related facial attributes, e.g., age, race, and gender. As part of an end-to-end system, a cGAN was designed to transform a given input facial expression to an "average" identity face with the same expression as the input. Then, identity-free FER is possible since the generated images have the same synthetic "average" identity and differ only in their displayed expressions. Experiments on four facial expression datasets, one with spontaneous expressions, show that IF-GAN outperforms the baseline CNN and achieves state-of-the-art performance for FER.

show abstract

FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion

Cited by 25 publications

References 63 publications

Orthogonal tucker decomposition using factor priors for 2D+3D facial expression recognition

Orthogonal tucker decomposition using factor priors for 2D+3D facial expression recognition

Multi-Feature Tensor Neighborhood Preserving Embedding for 3D Facial Expression Recognition

Identity-Free Facial Expression Recognition Using Conditional Generative Adversarial Network

Contact Info

Product

Resources

About