CoChat

Weight-Adapted Convolution Neural Network for Facial Expression Recognition in Human–Robot Interaction

Wu, Min, Su, Wanjuan, Chen, Luefeng, Liu, Zhentao, Cao, Weihua, Hirota, Kaoru · 2021 · IEEE Transactions on Systems, Man, and Cybernetics: Systems
Cited by 90

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Abstract

The weight-adapted convolution neural network (WACNN) is proposed to extract discriminative expression representations for recognizing facial expression. It aims to make good use of the convolution neural network's (CNN's) potential performance in avoiding local optima and speeding up convergence by the hybrid genetic algorithm (HGA) with optimal initial population, in such a way that it realizes deep and global emotion understanding in human-robot interaction. Moreover, the idea of novelty search is introduced to solve the deception problem in the HGA, which can expend the search space to help genetic algorithm jump out of local optimum and optimize large-scale parameters. In the proposal, the facial expression image preprocessing is conducted first, then the low-level expression features are extracted by using a principal component analysis. Finally, the high-level expression semantic features are extracted and recognized by WACNN which is optimized by HGA. In order to evaluate the effectiveness of WACNN, experiments on JAFFE, CK+, and static facial expressions in the wild 2.0 databases are carried out by using k -fold cross validation, and experimental results show the recognition accuracies of the proposal are superior to that of the state-of-the-art, such as local directional ternary pattern and weighted mixture deep neural network (DNN), which aim to extract discriminative and are the DNN-based methods. Moreover, recognition accuracies of the proposal are also higher than the deep CNN without HGA, which indicates that the proposal has better global optimization ability. Meanwhile, preliminary application experiments are also carried out by using the proposed algorithm on the emotional social robot system, where nine volunteers and two-wheeled robots experience the scenario of emotion understanding. Application results indicate that the wheeled robots can recognize basic expressions, such as happy, surprise, and so on.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tsmc.2019.2897330

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 49

  1. 10.1109/TSMC.2015.2406855 · DOI
  2. nesterov, 1983, A method of solving a convex programming problem with convergence rate $O(1/{k^{2}})$, Soviet Math Doklady, 27, 372
  3. 10.1109/TMM.2018.2844085 · DOI · Paper page
  4. 10.1109/ACCESS.2018.2805861 · DOI
  5. 10.1016/j.neucom.2015.02.011 · DOI · Paper page
  6. 10.1016/j.ins.2017.10.044 · DOI · Paper page
  7. 10.1016/j.neucom.2017.05.061 · DOI
  8. su, 2018, Nesterov accelerated gradient descent-based convolution neural network with dropout for facial expression recognition, Proc Asian Control Conf, 1063
  9. 10.1109/ACCESS.2017.2784096 · DOI · Paper page
  10. 10.1109/TCYB.2016.2625419 · DOI · Paper page
  11. 10.1049/iet-cvi.2016.0505 · DOI
  12. 10.1016/j.patcog.2016.12.002 · DOI
  13. 10.1109/TSMC.2016.2637279 · DOI
  14. 10.1109/TSMC.2017.2756447 · DOI
  15. 10.1109/TCYB.2017.2782661 · DOI
  16. 10.1109/TCYB.2014.2354351 · DOI · Paper page
  17. 10.1109/TAFFC.2014.2386334 · DOI · Paper page
  18. 10.1109/TAFFC.2017.2737540 · DOI
  19. 10.1016/j.jvcir.2017.10.008 · DOI
  20. 10.1016/j.eswa.2017.08.013 · DOI
  21. 10.1109/TNNLS.2015.2504724 · doi:10.1109/tnnls.2015.2504724
  22. 10.1109/TCYB.2014.2317174 · DOI
  23. 1998, The Japanese Female Facial Expression (Jaffe) Database
  24. 2011, Static Facial Expressions in the Wild 2 0 (SFEW 2 0) Database
  25. 10.1109/TFUZZ.2018.2809691 · DOI · Paper page
  26. 10.1109/TSMC.2018.2833384 · DOI
  27. 10.1109/TNNLS.2015.2492140 · DOI
  28. 10.1109/TEVC.2018.2808689 · DOI
  29. 10.1109/TNN.2005.860885 · DOI
  30. 10.1016/S0959-4388(02)00301-X · DOI · Paper page
  31. 10.1109/TEVC.2016.2601922 · DOI
  32. 10.1162/106365602320169811 · DOI · Paper page
  33. 10.1007/s10710-007-9028-8 · DOI · Paper page
  34. 10.1162/EVCO_a_00025 · DOI · Paper page
  35. 10.1016/j.ins.2018.05.057 · DOI
  36. 10.1016/j.asoc.2016.12.033 · DOI
  37. 10.1109/TSMCA.2012.2207107 · DOI
  38. 10.1109/TCYB.2016.2549639 · DOI · Paper page
  39. 10.1109/TCDS.2017.2728003 · DOI · Paper page
  40. 10.1016/j.neucom.2018.03.034 · DOI
  41. 10.1109/TIP.2017.2726010 · DOI · Paper page
  42. 2000, Cohn-Kanade (CK and CK+) database download site
  43. 10.1023/B:VISI.0000013087.49260.fb · DOI · Paper page
  44. srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res, 15, 1929
  45. 10.7551/mitpress/1090.001.0001 · DOI · Paper page
  46. 10.1109/TCYB.2017.2718037 · DOI
  47. 10.1016/j.patcog.2016.01.012 · DOI · Paper page
  48. 10.1109/TNNLS.2017.2695223 · DOI
  49. 10.1109/TNNLS.2015.2469673 · DOI · Paper page

Cited by

See all 90

Metadata

Authors
Wu, M., Su, W., Chen, L., Liu, Z., Cao, W., & Hirota, K.
Venue
IEEE Transactions on Systems, Man, and Cybernetics: Systems
Published
2021-03
Volume
51
Issue
3
Pages
1473-1484
ISSN
  • 2168-2216 (ISSN-L)
  • 2168-2232
OpenAlex
W2921644959
Cited by
90
References
5
FWCI
12.87
Type
journal article
Language
en
Open access
closed
Funders
  • National Natural Science Foundation of China (61603356, 61733016)
  • Higher Education Discipline Innovation Project (B17040)
  • Fundamental Research Funds for the Central Universities, China University of Geosciences, Wuhan (201839)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.