Abstract
A micro-expression (ME) is hard to fake and reflects people’s true feelings, micro-expression recognition (MER) is useful in a wide range of applications, such as medical research, criminal detection, and national security. Nevertheless, the existing deep learning methods based on deep neural networks (DNNs) fail to handle it, owing to the limited amount of training data and the black-box structure. In order to cope with these issues, this paper proposes a novel deep forest (DF) based on error-correcting output codes (ECOC), named EDF. The ECOC is innovatively deployed to encourage diversity and help to summarize differences among classes from multiple perspectives. Compared to DNN-based models, EDF is a more general solution for the MER since it is not sensitive to the size of data sets and needn’t other approaches such as transfer learning. On the other hand, EDF copies with the interpretability-accuracy trade-off to a certain extent. The experimental results on several data sets confirm that EDF outperforms most state-of-the-art methods. Furthermore, EDF is an interpretable method. It can reconstruct feature values by tracing and fusing the decision paths, from which we can easily determine important features. According to the results of the back-reconstruction process, the difference among classes can be summarized.
Similar content being viewed by others
References
Ben X, Jia X, Yan R, Zhang X, Meng W (2018) Learning effective binary descriptors for micro-expression recognition transferred by macro-information. Pattern Recogn Lett 107:50–58
Zong Y, Zheng W, Cui Z, Zhao G, Hu B (2020) Toward bridging microexpressions from different domains. IEEE Trans Cybernetics 50(12):5047–5060
Rolls E, Ekman P, Perrett D, Ellis H (1992) Facial expressions of emotion: an old controversy and new findings: discussion. Philosophical Trans Royal Soc London Series B 335:69–69
Wu Q, Shen X, Fu X (2011) The machine knows what you are hiding: an automatic micro-expression recognition system. In international conference on affective computing and intelligent interaction. 2011. Springer
Hurley CM, Anker AE, Frank MG, Matsumoto D, Hwang HC (2014) Background factors predicting accuracy and improvement in micro expression recognition. Motiv Emot 38(5):700–714
Zhang P, Ben X, Yan R, Wu C, Guo C (2016) Micro-expression recognition system. Optik-Int J Light Electron Optics 127(3):1395–1400
Liu YJ, Zhang JK, Yan WJ, Wang SJ, Zhao GY, Fu XL (2016) A main directional mean optical flow feature for spontaneous micro-expression recognition. IEEE Trans Affect Comput 7(4): 299–310
Zhao Y, Xu J (2019) An improved micro-expression recognition method based on necessary morphological patches. Symmetry 11(4):497
Peng M, Wang C, Chen T, Liu G, Fu X (2017) Dual temporal scale convolutional neural network for micro-expression recognition. Front Psychol 8:1745
Verburg M, Menkovski V (2019) Micro-expression detection in long videos using optical flow and recurrent neural networks. In 2019 14th IEEE International conference on automatic face & gesture recognition (FG 2019)
Min P, Zhan W, Zhang Z, Tong C (2018) From macro to micro expression recognition: deep learning on small datasets using transfer learning. In IEEE international conference on automatic face & gesture recognition
Khor HQ, See J, Phan R CW, Lin WY (2018) Enriched long-term recurrent convolutional network for facial micro-expression recognition. In proceedings 2018 13th IEEE international conference on automatic face & gesture recognition. IEEE 667–674
Wang C, Peng M, Bi T, Chen T (2020) Micro-attention for micro-expression recognition. Neurocomputing 410:354–362
Gan YS, Liong ST, Yau WC, Huang YC, Tan LK (2019) OFF-ApexNet on micro-expression recognition system. Signal Process-Image Commun 74:129–139
Wang XD, Zheng ZD, He Y, Yan F, Zeng ZQ, Yang Y (2021) Soft person reidentification network pruning via blockwise adjacent filter decaying. IEEE Trans Cybernetics
Liong S T, Gan Y S, See J, Khor H Q (2019) A shallow triple stream three-dimensional CNN (STSTNet) for micro-expression recognition system. In 2019 14th IEEE international conference on automatic face & gesture recognition (FG 2019)
Verma M, Vipparthi SK, Singh G, Murala S (2020) LEARNet: dynamic imaging network for micro expression recognition. IEEE Trans Image Process 29:1618–1627
Zhou ZH, Feng J (2019) Deep forest. Natl Sci Rev 6(1):74–86
Dietterich TG, Bakiri G (1994) Solving multiclass learning problems via error-correcting output codes. J Artif Intell Res 2:263–286
Sun M, Liong S, Liu K, Wu Q (2022) The heterogeneous ensemble of deep forest and deep neural networks for micro-expressions recognition. Appl Intell
Chen B, Liu KH, Xu Y, Wu QQ, Yao JF (2022) Block division convolutional network with implicit deep features augmentation for micro-expression recognition. IEEE Trans Mult
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Brunet N, Perez F, and Torre FD (2009) Learning Good Features for Active Shape Models, in 2009 IEEE 12th International Conference on Computer Vision Workshops. 206–211
Wathan J, Burrows AM, Waller BM, McComb K (2015) EquiFACS: the equine facial action coding system. PLoS One 10(8):e0131738
Ekman P and Friesen WV (1978) Facial action coding system: A technique for the measurement of facial movement. a technique for the measurement of facial action
Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recogn 29(1):51–59
Pfister T, Li XB, Zhao GY, Pietikainen M (2011) Recognising spontaneous facial micro-expressions. In 2011 international conference on computer vision. 1449–1456
Wang Y, See J, Phan R C W, Oh Y H (2014) Lbp with six intersection points: reducing redundant information in lbp-top for micro-expression recognition. In Asian conference on computer vision.
Huang X, Wang S, Liu X, Zhao G, Feng X, Pietikainen M (2017) Discriminative spatiotemporal local binary pattern with revisited integral projection for spontaneous facial micro-expression recognition. IEEE Trans Affect Comput 10(1):32–47
Polikovsky S, Kameda Y, and Ohta Y (2009) Facial micro-expressions recognition using high speed camera and 3D-gradient descriptor. In 3rd international conference on imaging for crime detection and prevention (ICDP 2009)
Liu YJ, Li BJ, Lai YK (2021) Sparse MDMO: learning a discriminative feature for micro-expression recognition. IEEE Trans Affect Comput 12(1):254–261
Xu F, Zhang J, Wang JZ (2017) Microexpression identification and categorization using a facial dynamics map. IEEE Trans Affect Comput 8(2):254–267
Zong Y, Huang X, Zheng W, Cui Z, Zhao G (2018) Learning from hierarchical spatiotemporal descriptors for micro-expression recognition. IEEE Trans Multimedia 20(11):3160–3172
Ding J, Tian Z, Lyu X, Wang Q, Zou B, Xie H (2019) Real-time micro-expression detection in unlabeled long videos using optical flow and LSTM neural network. In international conference on computer analysis of images and patterns. 2019. Springer
Liong S-T, See J, Wong KS, Phan RCW (2018) Less is more: micro-expression recognition from video using apex frame. Signal Process Image Commun 62:82–92
Liong ST, See J, Phan RCW, Le Ngo AC, Oh YH, Wong K(2014) Subtle expression recognition using optical strain weighted features. Computer vision - ACCV 2014 workshops. PT II 9009:644–657
Happy S, Routray A (2017) Fuzzy histogram of optical flow orientations for micro-expression recognition. IEEE Trans Affect Comput 10(3):394–406
Xia Z, Hong X, Gao X, Feng X, Zhao G (2020) Spatiotemporal recurrent convolutional networks for recognizing spontaneous micro-expressions. IEEE Trans Multimedia 22(3):626–640
Wang SJ, Li BJ, Liu YJ, Yan WJ, Ou X, Huang X, Xu F, Fu X (2018) Micro-expression recognition with small sample size by transferring long-term convolutional neural network. Neurocomputing 312:251–262
Xia ZQ, Peng W, Khor HQ, Feng XY, Zhao GY (2020) Revealing the invisible with model and data shrinking for composite-database micro-expression recognition. IEEE Trans Image Process 29:8590–8605
Quang NV, Chun J, Tokuyama T (2019) CapsuleNet for micro-expression recognition. In 14th IEEE international conference on automatic face and gesture recognition (FG 2019). Lille, FRANCE: IEEE 635–641
Li Y, Huang X, Zhao G (2021) Joint local and global information learning with single apex frame detection for micro-expression recognition. IEEE Trans Image Process 30:249–263
Utkin LV (2020) An imprecise deep forest for classification. Expert Syst Appl 141:112978
Ma C, Liu Z, Cao Z, Song W, Zhang J, Zeng W (2020) Cost-sensitive deep forest for price prediction. Pattern Recogn 107:107499
Wang HY, Tang Y, Jia ZY, Ye F (2020) Dense adaptive cascade forest: a self-adaptive deep ensemble for classification problems. Soft Comput 24(4):2955–2968
Yang L, Wu XZ, Jiang Y, Zhou ZH (2019) Multi-Label Learning with Deep Forest. In 24th European conference on artificial intelligence. 325:1634–1641
Gao J, Lin W, Liu K, Hong Q, Lin G, Wang B (2020) Imprecise deep Forest for partial label learning. IEEE Access 8:218530–218541
Zhou M, Zeng XH, Chen AZ (2019) Deep forest hashing for image retrieval. Pattern Recogn 95:114–127
Liu XO, Wang RL, Cai ZH, Cai YM, Yin X (2019) Deep multigrained Cascade Forest for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(10):8169–8183
Su R, Liu X, Wei L, Zou Q (2019) Deep-Resp-Forest: a deep forest model to predict anti-cancer drug response. Methods 166:91–102
Wang W, Dai QY, Li F, Xiong Y, Wei DQ (2020) MLCDForest: multi-label classification with deep forest in disease prediction for long non-coding RNAs. Brief Bioinform 22
Liu KH, Ye XN, Guo HZ, Wu QQ, Hong QQ (2021) The design of soft recoding-based strategies for improving error-correcting output codes. Appl Intell
Nazari S, Moin MS, Kanan HR (2018) Securing templates in a face recognition system using error-correcting output code and chaos theory. Comput Electrical Eng 72:644–659
Liu KH, Zhan WP, Liang YF, Zhang YN, Guo HZ, Yao JF,Wu QQ, Hong QQ (2021) The design of error-correcting output codes algorithm for the open-set recognition. Appl Intell
Yu H and Liu K (2017) Classification of multi-class microarray datasets using a minimizing class-overlapping based ECOC algorithm. In proceedings of the 5th international conference on bioinformatics and computational biology
Zhang ML, Fei Y, Tang CZ (2017) Disambiguation-free partial label learning. IEEE Trans Knowledge Data Eng 29(10):2155–2167
Feng J and Zhou ZH (2017) AutoEncoder by Forest. in AAAI-18
Yan W-J, Li X, Wang SJ, Zhao G, Liu YJ, Chen YH, Fu X (2014) CASME II: an improved spontaneous micro-expression database and the baseline evaluation. PLoS One 9(1):e86041
Li X, Pfister T, Huang X, Zhao G, Pietikäinen M (2013) A spontaneous micro-expression database: inducement, collection and baseline. In 2013 10th IEEE international conference and workshops on automatic face and gesture recognition (fg). IEEE
Davison AK, Lansley C, Costen N, Tan K, Yap MH (2016) Samm: a spontaneous micro-facial movement dataset. IEEE Trans Affect Comput 9(1):116–129
Zhao G, Pietikainen M (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Patt Analy Mach Intell 6:915–928
Zhou L, Mao Q, and Xue L (2019) Dual-Inception Network for Cross-Database Micro-Expression Recognition. in 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
Krizhevsky A, Sutskever I, and Hinton GE (2012) Imagenet classification with deep convolutional neural networks. in Advances in neural information processing systems
Iandola F N, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. arXiv. 1602.07360
Simonyan K and Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. (2015) Going deeper with convolutions. In proceedings of the IEEE conference on computer vision and pattern recognition
Demiar J, Schuurmans D (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30
Friedman M (1939) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Publ Am Stat Assoc 32(200):675–701
Friedman M (1940) A comparison of alternative tests of significance for the problem of $m$ rankings. Ann Math Stat 11(1):86–92
Nemenyi P (1963) Distribution-Eree multiple comparison. Biometrics
Díez-Pastor JF, Rodríguez JJ, García-Osorio CI, Kuncheva LI (2015) Diversity techniques improve the performance of the best imbalance learning ensembles. Inf Sci 325:98–117
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 61772023), National Key Research and Development Program of China (No. 2019QY1803) and Ministry of Science and Technology, Taiwan (MOST108-2221-E-035-066-, MOST108-2218-E-009-054-MY2, MOST 108-2218-E-035 -007-).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lin, WP., Ge, QC., Liong, ST. et al. The design of error-correcting output codes based deep forest for the micro-expression recognition. Appl Intell 53, 3488–3504 (2023). https://doi.org/10.1007/s10489-022-03590-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03590-5