Abstract
Emotion recognition from facial images is considered as a challenging task due to the varying nature of facial expressions. The prior studies on emotion classification from facial images using deep learning models have focused on emotion recognition from facial images but face the issue of performance degradation due to poor selection of layers in the convolutional neural network model.To address this issue, we propose an efficient deep learning technique using a convolutional neural network model for classifying emotions from facial images and detecting age and gender from the facial expressions efficiently. Experimental results show that the proposed model outperformed baseline works by achieving an accuracy of 95.65% for emotion recognition, 98.5% for age recognition, and 99.14% for gender recognition.
Similar content being viewed by others
Abbreviations
- h × w × d :
-
Height, width, and depth of input image
- K :
-
Filter matrix
- I :
-
Image matrix
- b :
-
Bias value
- R :
-
Nonlinear ReLU function
- ∘:
-
Convolutional operation
- F :
-
Feature map matrix
- max:
-
Maxpooling operator
- M:
-
Pooled feature matrix
- V:
-
Long feature vector
- n :
-
Net input
- x i :
-
Input vector
- w i :
-
Weight vector
- e ˗ n :
-
Input parameter exponent
References
Adil B, Nadjib KM, Yacine L (2019) A novel approach for facial expression recognition. In 2019 Inter Conf Net Adv Syst (ICNAS) pp 1–5. IEEE
All things Image (2019) Image Preprocessing, Image Data Generator class. Retrieved from https://keras.io/preprocessing/image/
All things Keras (2019) Keras Deep Learning Library Retrieved from https://keras.io/
Asghar MZ, Khan A, Bibi A, Kundi FM, Ahmad H (2017) Sentence-level emotion detection framework using rule-based classification. Cogn Comput 9(6):868–894
Avots E, Sapiński T, Bachmann M, Kamińska D (2019) Audiovisual emotion recognition in wild. Mach Vis Appl 30(5):975–985
Balasubramanian B, Diwan P, Nadar R, Bhatia A (2019) Analysis of Facial Emotion Recognition. In 2019 3rd Inter Conf Trends Elect Inform (ICOEI) pp 945–949. IEEE
Bouzakraoui MS, Sadiq A, Alaoui AY (2019) Appreciation of Customer Satisfaction Through Analysis Facial Expressions and Emotions Recognition. In 2019 4th World Conf Compl Syst (WCCS) pp 1–5. IEEE
Cadayona AM, Cerilla NMS, Jurilla DMM, Balan AKD, de Goma JC (2019) Emotional State Classification: An Additional Step in Emotion Classification through Face Detection. In 2019 IEEE 6th Inter Conf Indust Eng Appl (ICIEA) pp 667–671. IEEE
Chen J, Ou Q, Chi Z, Fu H (2017) Smile detection in the wild with deep convolutional neural networks. Mach Vis Appl 28(1–2):173–183
Das A, Dantcheva A, Bremond F (2018) Mitigating bias in gender, age and ethnicity classification: a multi-task convolution neural network approach. In Proc Euro Conf Comput Vis (ECCV) pp 0–0
Egger HL, Pine DS, Nelson E, Leibenluft E, Ernst M, Towbin KE, Angold A (2011) The NIMH Child Emotional Faces Picture Set (NIMH-ChEFS): a new set of children’s facial emotion stimuli. Int J Methods Psychiatr Res 20(3):145–156
Fathallah A, Abdi L, Douik A (2017) Facial Expression Recognition via Deep Learning. In Computer Systems and Applications (AICCSA), 2017 IEEE/ACS 14th Inter Conf Comput Syst Appl pp 745–750. IEEE
Guo J, Lei Z, Wan J, Avots E, Hajarolasvadi N, Baro X (2018) Dominant and Complementary Emotion Recognition From Still Images of Faces
Guo JM, Huang PC, Chang LY (2019) A Hybrid Facial Expression Recognition System Based on Recurrent Neural Network. In 2019 16th IEEE Inter Conf Adv Vid Signal Based Surv (AVSS) pp 1–8. IEEE
Hossain MS, Muhammad G (2019) Emotion recognition using deep learning approach from audio–visual emotional big data. Information Fusion 49:69–78
Joseph A, Geetha P (2020) Facial emotion detection using modified eyemap–mouthmap algorithm on an enhanced image and classification with tensorflow. Vis Comput 36(3):529–539
Kanade T, Cohn JF, Tian Y (2000) Comprehensive database for facial expression analysis.Proceedings of the Fourth IEEE Inter Conf Auto Face Gesture Recognit (FG'00) Grenoble, France 46–53
Kolodziej M, Majkowski A, Rak RJ, Tarnowski P, Pielaszkiewicz T (2018) Analysis of facial features for the use of emotion recognition. In 19th Inter Conf Comput Prob Elect Eng pp 1–4. IEEE
Kumar A, Jaiswal A (2017) Image sentiment analysis using convolutional neural network. In Inter Conf Intel Syst Des Appl pp 464–473. Springer, Cham
Kuo PH, Tsai TN, Luan PC (2019) CNN and LSTM Based Facial Expression Analysis Model for a Humanoid Robot. IEEE Access 7:93998–94011
Li THS, Kuo PH, Tsai TN, Luan PC (2019) CNN and LSTM Based Facial Expression Analysis Model for a Humanoid Robot. IEEE Access 7:93998–94011
Liu KC, Hsu CC, Wang WY, Chiang HH (2019) Real-Time facial expression recognition based on cnn. In 2019Inter Conf Syst Sci Eng (ICSSE) pp 120–123. IEEE
Lopez-Martin M, Carro B, Sanchez-Esguevillas A, Lloret J (2017) Network traffic classifier with convolutional and recurrent neural networks for Internet of Things. IEEE Access 5:18042–18050
Lopez-Rincon A (2019) Emotion recognition using facial expressions in children using the NAO Robot. In 2019 Inter Conf Elect Commun Comput (CONIELECOMP) pp 146–153). IEEE
Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) Subedi sanjay. Large Scale Face Dataset for Age and gender. UTKFace dataset. Retrieved from https://www.kaggle.com/jangedoo/utkface-new
Lyons M, Akamatsu S, Kamachi M, Gyoba J (1998, April) Coding facial expressions with gabor wavelets. In Proceedings Third IEEE international conference on automatic face and gesture recognition (pp. 200–205). IEEE
Mellouk W, Handouzi W (2020) Facial emotion recognition using deep learning: review and insights. Procedia Comput Sci 175:689–694
Nadjib KM, Yacine L (2019) A novel approach for facial expression recognition. In 2019 Inter Conf Net Adv Syst (ICNAS) pp 1–5. IEEE
Nithyashri J, Kulanthaivel G (2012) Classification of human age based on Neural Network using FG-NET Aging database and Wavelets. In 2012 Fourth Inter Conf Adv Comput (ICoAC) pp 1–5. IEEE
Ozdemir MA, Elagoz B, Alaybeyoglu A, Sadighzadeh R, Akan A (2019) Real Time Emotion Recognition from Facial Expressions Using CNN Architecture. In 2019 Med Technol Cong (TIPTEKNO) pp 1–4. IEEE
Papapicco C, Mininni G (2020) Impact memes: phds humor (e). Multi Tools Appl 1–22
Pathar R, Adivarekar A, Mishra A, Deshmukh A (2019) Human Emotion Recognition using Convolutional Neural Network in Real Time. In 2019 1st Inter Conf Innov Inform Commun Technol (ICIICT) pp 1–7. IEEE
Patil M, Veni S (2019) Driver Emotion Recognition for Enhancement of Human Machine Interface in Vehicles. In 2019Inter Conf Commun Signal Proc (ICCSP) pp 0420–0424. IEEE
Prabhu R (2018) Understanding of Convolutional Neural Network (CNN) — Deep Learning. Retrieved from https://medium.com/@RaghavPrabhu/understanding-of-convolutional-neural-network-cnn-deep-learning-99760835f148
Rao A (2019) Convolutional Neural Network Tutorial (CNN) – Developing An Image Classifier In Python Using Tensor Flow Retrieved from https://www.edureka.co/blog/convolutional-neural-network/
Rasamoelina AD, Adjailia F, SinČàk P (2019) Deep Convolutional Neural Network for Robust Facial Emotion Recognition. In 2019 IEEE Inter Symp Innov Intel Syst Appl (INISTA) pp 1–6. IEEE
Shan K, Guo J, You W, Lu D, Bie R (2017) Automatic facial expression recognition based on a deep convolutional-neural-network structure. In 2017 IEEE 15th Inter Conf Soft Eng Res Manage Appl (SERA) pp 123–128. IEEE
Sinha S, Kumar R, Nalawade S, Ray D (2017) Facial Expression Recognition. Inter Res J Eng Technol Volume 04, p ISSN: 2395–0072. IRJET
Taha B, Hatzinakos D (2019) Emotion Recognition from 2D Facial Expressions. In 2019 IEEE Can Conf Elect Comput Eng (CCECE) pp 1–4. IEEE
Tripathi S, Acharya S, Sharma RD, Mittal S, Bhattacharya S (2017) Using Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Dataset. In AAAI pp 4746–4752
Verma A, Singh P, Alex JSR (2019) Modified Convolutional Neural Network Architecture Analysis for Facial Emotion Recognition. In 2019 Inter Conf Syst Signals Image Proc (IWSSIP) pp 169–173. IEEE
Wu C, Chai L, Yang J, Sheng Y (2019) Facial Expression Recognition using Convolutional Neural Network on Graphs. In 2019 Chin Cont Conf (CCC) pp 7572-7576. IEEE
Wu H, Zhao J (2018) Deep convolutional neural network model based chemical process fault diagnosis. Comput Chem Eng 115:185–197
Xue D, Bagamian N, Broder A (2016) Classification of Emotion from Facial Images
Yarlagadda A, Murthy JVR, Prasad MK (2015) A novel method for human age group classification based on Correlation Fractal Dimension of facial edges. J king Saud University Comput Inform Sci 27(4):468–476
Yang Z, Zhang Y, Luo J (2019) Human-Centered Emotion Recognition in Animated GIFs. In 2019 IEEE Inter Conf Multi Expo (ICME) pp 1090–1095. IEEE
Yin L, Wei X, Sun Y, Wang J, Rosato MJ (2006) A 3D facial expression database for facial behavior research. In 7th inter Conf Auto Face Gesture recognit (FGR06) pp 211–216. IEEE
Zadeh MMT, Imani M, Majidi B (2019) Fast Facial emotion recognition Using Convolutional Neural Networks and Gabor Filters. In 2019 5th Conf Knowl Based Eng Innov (KBEI) pp 577–581. IEEE
Zhong L, Bai C, Li J, Chen T, Li S, Liu Y (2019) A Graph-Structured Representation with BRNN for Static-based Facial Expression Recognition. In 2019 14th IEEE Inter Conf Auto Face Gesture Recognit (FG 2019) pp 1–5. IEEE
Zhu L, Yu W, Zhang C, Zhang Z, Huang F, Yu H (2019) SVS-JOIN: Efficient Spatial Visual Similarity Join for Geo-Multimedia. IEEE Access 7:158389–158408
Acknowledgements
This Research work was supported by Zayed University Research Incentives Fund# R19096
Author information
Authors and Affiliations
Corresponding author
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
Khattak, A., Asghar, M.Z., Ali, M. et al. An efficient deep learning technique for facial emotion recognition. Multimed Tools Appl 81, 1649–1683 (2022). https://doi.org/10.1007/s11042-021-11298-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11298-w