{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:02:49Z","timestamp":1760241769491,"version":"build-2065373602"},"reference-count":59,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2018,9,19]],"date-time":"2018-09-19T00:00:00Z","timestamp":1537315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100016221","name":"UPB","doi-asserted-by":"publisher","award":["UPB\u2014GEX2017, Ctr. No. 22\/2017 (SET)"],"award-info":[{"award-number":["UPB\u2014GEX2017, Ctr. No. 22\/2017 (SET)"]}],"id":[{"id":"10.13039\/501100016221","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The detection of human emotions has applicability in various domains such as assisted living, health monitoring, domestic appliance control, crowd behavior tracking real time, and emotional security. The paper proposes a new system for emotion classification based on a generative adversarial network (GAN) classifier. The generative adversarial networks have been widely used for generating realistic images, but the classification capabilities have been vaguely exploited. One of the main advantages is that by using the generator, we can extend our testing dataset and add more variety to each of the seven emotion classes we try to identify. Thus, the novelty of our study consists in increasing the number of classes from N to 2N (in the learning phase) by considering real and fake emotions. Facial key points are obtained from real and generated facial images, and vectors connecting them with the facial center of gravity are used by the discriminator to classify the image as one of the 14 classes of interest (real and fake for seven emotions). As another contribution, real images from different emotional classes are used in the generation process unlike the classical GAN approach which generates images from simple noise arrays. By using the proposed method, our system can classify emotions in facial images regardless of gender, race, ethnicity, age and face rotation. An accuracy of 75.2% was obtained on 7000 real images (14,000, also considering the generated images) from multiple combined facial datasets.<\/jats:p>","DOI":"10.3390\/sym10090414","type":"journal-article","created":{"date-parts":[[2018,9,19]],"date-time":"2018-09-19T10:50:31Z","timestamp":1537354231000},"page":"414","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation"],"prefix":"10.3390","volume":"10","author":[{"given":"Traian","family":"Caramihale","sequence":"first","affiliation":[{"name":"Department of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Popescu","sequence":"additional","affiliation":[{"name":"Department of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Loretta","family":"Ichim","sequence":"additional","affiliation":[{"name":"Department of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1109\/34.598235","article-title":"Face recognition by elastic bunch graph matching","volume":"19","author":"Wiskott","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","unstructured":"(2018, March 21). Face Recognition Market by Component, Technology, Use Case, End-User, and Region\u2013Global Forecast to 2022. Available online: https:\/\/www.marketsandmarkets.com\/Market-Reports\/facial-recognition-market-995.html."},{"key":"ref_3","first-page":"775","article-title":"Detecting Faces in Images: A survey","volume":"19","author":"Yang","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","first-page":"6694","article-title":"A study of various face detection methods","volume":"3","author":"Gupta","year":"2014","journal-title":"Int. J. Adv. Res. Comput. Commun. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"61","DOI":"10.14257\/ijca.2015.8.5.07","article-title":"A survey of feature base methods for human face detection","volume":"8","author":"Hiyam","year":"2015","journal-title":"Int. J. Control Autom."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Smrti, T., and Nitin, M. (2016). Detection, segmentation and recognition of face and its features using neural network. J. Biosens. Bioelectron., 7.","DOI":"10.4172\/2155-6210.1000210"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Le, T.H. (2011). Applying Artificial Neural Networks for Face Recognition. Adv. Artif. Neural Syst.","DOI":"10.1155\/2011\/673016"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Farfade, S.S., Saberian, M., and Li, L.J. (2015, January 23\u201326). Multiview face detection using deep convolutional neural networks. Proceedings of the 5th International Conference on Multimedia Retrieval (ICMR), Shanghai, China.","DOI":"10.1145\/2671188.2749408"},{"key":"ref_9","unstructured":"Martinez-Gonzalez, A.N., and Ayala-Ramirez, V. (December, January 26). Real time face detection using neural networks. Proceedings of the 10th Mexican International Conference on Artificial Intelligence, Puebla, Mexico."},{"key":"ref_10","first-page":"81","article-title":"Face recognition using neural network: A review","volume":"10","author":"Kasar","year":"2016","journal-title":"Int. J. Secur. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Al-Allaf, O.N. (2014). Review of face detection systems based artificial neural networks algorithms. Int. J. Multimed. Appl., 6.","DOI":"10.5121\/ijma.2014.6101"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Prihasto, B., Choirunnisa, S., Nurdiansyah, M.I., Mathulapragsan, S., Chu, V.C., Chen, S.H., and Wang, J.C. (2016, January 17\u201320). A survey of deep face recognition in the wild. Proceedings of the 2016 International Conference on Orange Technologies, Melbourne, Australia.","DOI":"10.1109\/ICOT.2016.8278983"},{"key":"ref_13","unstructured":"Fu, Z.P., Zhang, Y.N., and Hou, H.Y. (2014, January 20\u201323). Survey of deep learning in face recognition. Proceedings of the 2014 International Conference on Orange Technologies, Xi\u2019an, China."},{"key":"ref_14","unstructured":"Wang, M., and Deng, W. (arXiv, 2018). Deep face recognition: A survey, arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.3390\/sym7031475","article-title":"Performance enhancement of face recognition in smart TV using symmetrical fuzzy-based quality assessment","volume":"7","author":"Kim","year":"2015","journal-title":"Symmetry"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hong, H.G., Lee, W.O., Kim, Y.G., Kim, K.W., Nguyen, D.T., and Park, K.R. (2016). Fuzzy system-based face detection robust to in-plane rotation based on symmetrical characteristics of a face. Symmetry, 8.","DOI":"10.3390\/sym8080075"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sharifi, O., and Eskandari, M. (2018). Cosmetic Detection framework for face and iris biometrics. Symmetry, 10.","DOI":"10.3390\/sym10040122"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, L., He, R., and Tan, T. (arXiv, 2018). Anti-Makeup: Learning a bi-level adversarial network for makeup-invariant face verification, arXiv.","DOI":"10.1609\/aaai.v32i1.12294"},{"key":"ref_19","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (arXiv, 2014). Generative Adversial Nets, arXiv."},{"key":"ref_20","unstructured":"Odena, A., Olah, C., and Shlens, J. (arXiv, 2016). Conditional Image Synthesis with Auxiliary Classifier GANs, arXiv."},{"key":"ref_21","unstructured":"Gauthier, J. (2018, April 15). Conditional Generative Adversarial Nets for Convolutional Face Generation. Available online: http:\/\/cs231n.stanford.edu\/reports\/2015\/pdfs\/jgauthie_final_report.pdf."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Antipov, G., Baccouche, M., and Dugelay, J.L. (arXiv, 2017). Face aging with conditional generative adversarial networks, arXiv.","DOI":"10.1109\/ICIP.2017.8296650"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, E., Zhang, S., Li, T., and He, R. (arXiv, 2017). Beyond face rotation: Global and local perception gan for photorealistic and identity preserving frontal view synthesis, arXiv.","DOI":"10.1109\/ICCV.2017.267"},{"key":"ref_24","unstructured":"Li, Z., and Luo, Y. (arXiv, 2017). Generate identity-preserving faces by generative adversarial networks, arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, J., Yacoob, Y., and Jacobs, D.W. (arXiv, 2017). Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images, arXiv.","DOI":"10.1109\/CVPR.2018.00653"},{"key":"ref_26","unstructured":"Zhang, W., Shu, Z., Samaras, D., and Chen, L. (arXiv, 2017). Improving heterogeneous face recognition with conditional adversial networks, arXiv."},{"key":"ref_27","unstructured":"Springenberg, J.T. (arXiv, 2015). Unsupervised and semi-supervised learning with categorical generative adversarial networks, arXiv."},{"key":"ref_28","unstructured":"Radford, A., Metz, L., and Chintala, S. (arXiv, 2015). Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv."},{"key":"ref_29","unstructured":"Odena, A. (arXiv, 2016). Semi-supervised learning with generative adversarial networks, arXiv."},{"key":"ref_30","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (arXiv, 2016). Improved techniques for training Gans, arXiv."},{"key":"ref_31","unstructured":"Papernot, N., Abadi, M., Erlingsson, U., Goodfellow, I., and Talwar, K. (arXiv, 2016). Semi-supervised knowledge transfer for deep learning from private training data, arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fredrickson, B.L. (2003). Cultivating positive emotions to optimize health and well-being. Prev. Treat., 3.","DOI":"10.1037\/1522-3736.3.1.31a"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1080\/026999398379718","article-title":"Positive emotions speed recovery from the cardiovascular sequelae of negative emotions","volume":"12","author":"Fredrickson","year":"1998","journal-title":"Cogn. Emot."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1037\/0033-2909.129.1.10","article-title":"Understanding the association between socioeconomic status and physical health: Do negative emotions play a role?","volume":"129","author":"Gallo","year":"2003","journal-title":"Psychol. Bull."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1016\/S0002-9149(03)00967-6","article-title":"Effect of negative emotions on frequency of coronary heart disease (The Normative Aging Study)","volume":"92","author":"Todaro","year":"2003","journal-title":"Am. J. Cardiol."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Huang, Y., and Khan, S.M. (2017, January 21\u201326). DyadGAN: Generating facial expressions in dyadic interactions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.280"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Shi, B.E. (arXiv, 2017). Photorealistic facial expression synthesis by the conditional difference adversarial autoencoder, arXiv.","DOI":"10.1109\/ACII.2017.8273626"},{"key":"ref_38","unstructured":"Lu, Y., Tai, Y.W., and Tang, C.K. (arXiv, 2017). Conditional CycleGAN for attribute guided face image generation, arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ding, H., Sricharan, K., and Chellappa, R. (arXiv, 2017). ExprGAN: Facial expression editing with controllable expression intensity, arXiv.","DOI":"10.1609\/aaai.v32i1.12277"},{"key":"ref_40","unstructured":"Xu, R., Zhou, Z., Zhang, W., and Yu, Y. (arXiv, 2017). Face transfer with generative adversarial network, arXiv."},{"key":"ref_41","unstructured":"Nojavanasghari, B., Huang, Y., and Khan, S.M. (arXiv, 2018). Interactive generative adversarial networks for facial expression generation in dyadic interactions, arXiv."},{"key":"ref_42","unstructured":"Tian, Y.L., Kanage, T., and Cohn, J. (2000, January 8\u201311). Robust Lip Tracking by Combining Shape, Color and Motion. Proceedings of the 4th Asian Conference on Computer Vision, Taipei, Taiwan."},{"key":"ref_43","unstructured":"Agarwal, M., Krohn-Grimberghe, A., and Vyas, R. (arXiv, 2017). Facial key points detection using deep convolutional neural network\u2014Naimishnet, arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Kazemi, V., and Sullivan, J. (2014, January 23\u201328). One millisecond face alignment with an ensemble of regression trees. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Suh, K.H., Kim, Y., and Lee, E.C. (2016). Facial feature movements caused by various emotions: Differences according to sex. Symmetry, 8.","DOI":"10.3390\/sym8090086"},{"key":"ref_46","unstructured":"Dachapally, P.R. (arXiv, 2017). Facial emotion detection using convolutional neural networks and representational autoencoder units, arXiv."},{"key":"ref_47","unstructured":"Lyons, M.J., Kamachi, M., and Gyoba, J. (2018, April 15). Japanese Female Facial Expressions (JAFFE). Available online: http:\/\/www.kasrl.org\/jaffe.html."},{"key":"ref_48","unstructured":"Huang, G.B., Ramesh, M., Berg, T., and Learned-Miller, E. (2008). Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments, Workshop on Faces in \u2019RealLife\u2019 Images: Detection, Alignment, and Recognition."},{"key":"ref_49","unstructured":"Zhu, X., Liu, Y., Qin, Z., and Li, J. (arXiv, 2017). Data augmentation in emotion classification using generative adversarial networks, arXiv."},{"key":"ref_50","unstructured":"(2017, October 19). Facial Expression Recognition (FER2013) Dataset. Available online: https:\/\/www.kaggle.com\/c\/challenges-in-representation-learning-facial-expression-recognition-challenge\/data."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Lee, K.W., Hong, H.G., and Park, K.R. (2017). Fuzzy system-based fear estimation based on the symmetrical characteristics of face and facial feature points. Symmetry, 9.","DOI":"10.3390\/sym9070102"},{"key":"ref_52","unstructured":"Al-Shabi, M., Cheah, W.P., and Connie, T. (arXiv, 2016). Facial expression recognition using a hybrid CNN-SIFT aggregator, arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., and Matthews, I. (2010, January 13\u201318). The Extended Cohn-Kanade Dataset (CK+); A Complete Dataset for Action Unit and Emotion-Specified Expression. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, San Francisco, CA, USA.","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Dhal, A., Goecke, R., Luvey, S., and Gedeon, T. (2011, January 6\u201313). Static facial expressions in tough; data, evaluation protocol and benchmark. Proceedings of the IEEE International Conference on Computer Vision ICCV2011, Barcelona, Spain.","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Mishra, S., Prasada, G.R.B., Kumar, R.K., and Sanyal, G. (2017, January 13\u201315). Emotion Recognition through facila gestures\u2014A deep learning approach. Proceedings of the Fifth International Conference on Mining Intelligence and Knowledge Exploration (MIKE), Hyderabad, India.","DOI":"10.1007\/978-3-319-71928-3_2"},{"key":"ref_56","unstructured":"Quinn, M.A., Sivesind, G., and Reis, G. (2018, April 15). Real-Time Emotion Recognition from Facial Expressions. Available online: http:\/\/cs229.stanford.edu\/proj2017\/final-reports\/5243420.pdf."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1511\/2001.28.344","article-title":"The nature of emotions","volume":"89","author":"Plutschik","year":"2001","journal-title":"Am. Sci."},{"key":"ref_58","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (arXiv, 2016). InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, arXiv."},{"key":"ref_59","unstructured":"(2017, November 12). Dlib Library. Available online: http:\/\/blog.dlib.net\/2014\/08\/real-time-face-pose-estimation.html."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/10\/9\/414\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:21:23Z","timestamp":1760196083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/10\/9\/414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,19]]},"references-count":59,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9]]}},"alternative-id":["sym10090414"],"URL":"https:\/\/doi.org\/10.3390\/sym10090414","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2018,9,19]]}}}