<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2022-22-1-120-126</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-282</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Распознавание эмоционального состояния человека на основе сверточной нейронной сети</article-title><trans-title-group xml:lang="en"><trans-title>Recognition of the emotional state based on a convolutional neural network</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-9004-3554</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сома</surname><given-names>Г. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Soma</surname><given-names>G. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сома Гедеш Мануэл — аспирант</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Guedes M. Soma — PhD Student</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">guedes.soma@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7758-6578</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Каднова</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Kadnova</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Каднова Айжана Михайловна — научный сотрудник; кандидат технических наук, преподаватель</p><p>sc 57217115500</p><p>Санкт-Петербург, 197101</p><p>Воронеж, 394065</p></bio><bio xml:lang="en"><p>Aizhana M. Kadnova — Scientific Researcher; PhD, Lecturer</p><p>sc 57217115500</p><p>Saint Petersburg, 197101</p><p>Voronezh, 394065</p></bio><email xlink:type="simple">aizhana_kadnova@mail.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Университет ИТМО; Воронежский институт МВД России</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University; Voronezh Institute of the Ministry of Internal Affairs of Russia</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2022</year></pub-date><pub-date pub-type="epub"><day>17</day><month>12</month><year>2024</year></pub-date><volume>22</volume><issue>1</issue><fpage>120</fpage><lpage>126</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Сома Г.М., Каднова А.М., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Сома Г.М., Каднова А.М.</copyright-holder><copyright-holder xml:lang="en">Soma G.M., Kadnova A.M.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/282">https://ntv.elpub.ru/jour/article/view/282</self-uri><abstract><p>Предмет исследования. Предложено новое решение распознавания эмоционального состояния человека (радость, удивление, грусть, гнев, отвращение, страх и нейтральное состояние) по выражению лица. Наряду с традиционной вербальной коммуникацией эмоции играют значительную роль при определении истинных намерений для реализации коммуникативного акта в различных практических сферах деятельности. Существует большое количество моделей и алгоритмов распознавания эмоций человека по классам и их применения для сопровождения коммуникативного акта. Известные модели дают невысокую точность распознавания эмоциональных состояний. Методы. Для классификации выражений лиц построены два классификатора, реализованные в библиотеке Keras: ResNet50, MobileNet, и предложена новая архитектура классификатора сверточной нейронной сети. Обучение классификаторов осуществлено на наборе данных FER 2013. Основные результаты. Сравнение результатов работы выбранных классификаторов показало, что предложенная модель имеет наилучший результат по точности валидации (60,13 %) и размеру (15,49 МБ), при этом функция потерь составляет 0,079 для точности и 2,80 — для валидации. Практическая значимость. Результаты исследования могут быть использованы для распознавания признаков стресса и агрессивного поведения человека в системах обслуживания населения и в сферах, при наличии общения с большим количеством людей.</p></abstract><trans-abstract xml:lang="en"><p>The paper proposes a new solution for recognizing the emotional state of a person (joy, surprise, sadness, anger, disgust, fear, and neutral state) by facial expression. Along with traditional verbal communication, emotions play a significant role in determining true intentions during a communicative act in various areas. There is a large number of models and algorithms for recognizing human emotions by class and applying them to accompany a communicative act. The known models show a low accuracy in recognizing emotional states. To classify facial expressions, two classifiers were built and implemented in the Keras library (ResNet50, MobileNet) and a new architecture of a convolutional neural network classifier was proposed. The classifiers were trained on the FER 2013 dataset. Comparison of the results for the chosen classifiers showed that the proposed model has the best result in terms of validation accuracy (60.13 %) and size (15.49 MB), while the loss function is 0.079 for accuracy and 2.80 for validation. The research results can be used to recognize signs of stress and aggressive human behavior in public service systems and in areas characterized by the need to communicate with a large number of people.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>ResNet50</kwd><kwd>MobileNet</kwd><kwd>выражение лица</kwd><kwd>глубокая нейронная сеть</kwd><kwd>эмоция</kwd><kwd>классификация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>ResNet50</kwd><kwd>MobileNet</kwd><kwd>facial expressions</kwd><kwd>deep neural network</kwd><kwd>emotion</kwd><kwd>classification</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено за счет гранта Российского научного фонда (проект № 22-21-00604).</funding-statement><funding-statement xml:lang="en">This research is financially supported by the Russian Science Foundation, Agreement No. 22-21-00604.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Varma S., Shinde M., Chavan S.S. Analysis of PCA and LDA features for facial expression recognition using SVM and HMM classifiers // Techno-Societal 2018: Proc. of the 2nd International Conference on Advanced Technologies for Societal Applications. V. 1. 2020. P. 109–119. https://doi.org/10.1007/978-3-030-16848-3_11</mixed-citation><mixed-citation xml:lang="en">Varma S., Shinde M., Chavan S.S. Analysis of PCA and LDA features for facial expression recognition using SVM and HMM classifiers. Techno-Societal 2018. Proc. of the 2nd International Conference on Advanced Technologies for Societal Applications. Vol. 1, 2020, pp. 109–119. https://doi.org/10.1007/978-3-030-16848-3_11</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Рюмина Е.В., Карпов А.А. Аналитический обзор методов распознавания эмоций по выражениям лица человека // Научно-технический вестник информационных технологий, механики и оптики. 2020. Т. 20. № 2. С. 163–176. https://doi.org/10.17586/2226–1494-2020-20-2-163-176</mixed-citation><mixed-citation xml:lang="en">Ryumina E.V. Karpov A.A Analytical review of methods for emotion recognition by human face expressions. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2020, vol. 20, no. 2, pp. 163–176. (in Russian ). https://doi.org/10.17586/2226–1494-2020-20-2-163-176</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Ахметшин Р.И., Кирпичников А.П., Шлеймович М.П. Распознавание эмоций человека на изображениях // Вестник технологического университета. 2015. Т. 18. № 11. С. 160–163.</mixed-citation><mixed-citation xml:lang="en">Akhmetshin R.I., Kirpichnikov A.P., Shleimovich M.P. Human emotion recognition in images. Vestnik Technologicheskogo Universiteta, 2015, vol. 18, no. 11, pp. 160–163. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Эрман Е.А., Мамдух Мохаммед Гомаа Мохаммед. Метод обнаружения лиц на изображении с использованием комбинации метода Виолы-Джонса и алгоритмов определения цвета кожи // Вестник Астраханского государственного технического университета. Серия: Управление, вычислительная техника и информатика. 2015. № 1. С. 49–55.</mixed-citation><mixed-citation xml:lang="en">Erman E.A., Mamdouh Mokhammed Gomaa Mokhammed. Face detection in image by using a combination of Viola — Jones method and skin detection algorithms. Vestnik of Astrakhan State Technical University. Series: Management, Computer Sciences and Informatics, 2015, no. 1, pp. 49–55. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Мухамадиева К.Б. Сравнительный анализ алгоритмов распознавания лиц // Современные материалы, техника и технологии. 2017. № 7(15). С. 58–62.</mixed-citation><mixed-citation xml:lang="en">Mukhamadieva K.B. Comparative analysis of facial recognition algorithms. Modern Materials, Equipment, and Technology, 2017, no. 7(15), pp. 58–62. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Амелькин С.А., Захаров А.В., Хачумов В.М. Обобщенное расстояние Евклида Махаланобиса и его свойства // Информационные технологии и вычислительные системы. 2006. № 4. С. 40–44.</mixed-citation><mixed-citation xml:lang="en">Amelkin S. A., Zakharov A.V., Khachumov V.M. Generalized Mahalanobis Euclidean distance and its properties. Information Technologies and Computer Systems, 2006, no. 4, pp. 40–44. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Karamizadeh S., Abdullah S.M., Manaf A.A., Zamani M., Hooman A. An overview of principal component analysis // Journal of Signal and Information Processing. 2013. V. 4. P. 173–175. https://doi.org/10.4236/jsip.2013.43B031</mixed-citation><mixed-citation xml:lang="en">Karamizadeh S., Abdullah S.M., Manaf A.A., Zamani M., Hooman A. An overview of principal component analysis // Journal of Signal and Information Processing. 2013. V. 4. P. 173–175. https://doi.org/10.4236/jsip.2013.43B031</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Dino H.I., Abdulrazzaq M.B. Facial expression classification based on SVM, KNN and MLP classifiers // Proc. of the International Conference on Advanced Science and Engineering (ICOASE 2019). 2019. P. 70–75. https://doi.org/10.1109/ICOASE.2019.8723728</mixed-citation><mixed-citation xml:lang="en">Dino H.I., Abdulrazzaq M.B. Facial expression classification based on SVM, KNN and MLP classifiers // Proc. of the International Conference on Advanced Science and Engineering (ICOASE 2019). 2019. P. 70–75. https://doi.org/10.1109/ICOASE.2019.8723728</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Greche L., Es-Sbai N., Lavendelis E. Histogram of oriented gradient and multi layer feed forward neural network for facial expression identification // Proc. of the International Conference on Control, Automation and Diagnosis (ICCAD 2017). 2017. P. 333–337. https://doi.org/10.1109/CADIAG.2017.8075680</mixed-citation><mixed-citation xml:lang="en">Greche L., Es-Sbai N., Lavendelis E. Histogram of oriented gradient and multi layer feed forward neural network for facial expression identification // Proc. of the International Conference on Control, Automation and Diagnosis (ICCAD 2017). 2017. P. 333–337. https://doi.org/10.1109/CADIAG.2017.8075680</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Greche L., Akil M., Kachouri R., Es-Sbai N. A new pipeline for the recognition of universal expressions of multiple faces in a video sequence // Journal of Real-Time Image Processing. 2020. V. 17. N 5. P. 1389–1402. https://doi.org/10.1007/s11554-019-00896-5</mixed-citation><mixed-citation xml:lang="en">Greche L., Akil M., Kachouri R., Es-Sbai N. A new pipeline for the recognition of universal expressions of multiple faces in a video sequence // Journal of Real-Time Image Processing. 2020. V. 17. N 5. P. 1389–1402. https://doi.org/10.1007/s11554-019-00896-5</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Kulke L., Brümmer L., Pooresmaeili A., Schacht A. Overt and covert attention shifts to emotional faces: Combining EEG, eye tracking, and a go/no-go paradigm // Psychophysiology. 2021. V. 58. N 8. P. e13838. https://doi.org/10.1111/psyp.13838</mixed-citation><mixed-citation xml:lang="en">Kulke L., Brümmer L., Pooresmaeili A., Schacht A. Overt and covert attention shifts to emotional faces: Combining EEG, eye tracking, and a go/no-go paradigm // Psychophysiology. 2021. V. 58. N 8. P. e13838. https://doi.org/10.1111/psyp.13838</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Aleksic P.S., Katsaggelos A.K. Automatic facial expression recognition using facial animation parameters and multistream HMMs // IEEE Transactions on Information Forensics and Security. 2006. V. 1. N 1. P. 3–11. https://doi.org/10.1109/TIFS.2005.863510</mixed-citation><mixed-citation xml:lang="en">Aleksic P.S., Katsaggelos A.K. Automatic facial expression recognition using facial animation parameters and multistream HMMs // IEEE Transactions on Information Forensics and Security. 2006. V. 1. N 1. P. 3–11. https://doi.org/10.1109/TIFS.2005.863510</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Gardner M.W., Dorling S.R. Artificial neural networks (the multilayer perceptron) — a review of applications in the atmospheric sciences // Atmospheric Environment. 1998. V. 32. N 14-15. P. 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0</mixed-citation><mixed-citation xml:lang="en">Gardner M.W., Dorling S.R. Artificial neural networks (the multilayer perceptron) — a review of applications in the atmospheric sciences // Atmospheric Environment. 1998. V. 32. N 14-15. P. 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Cao H., Cooper D.G., Keutmann M.K., Gur R.C., Nenkova A., Verma R. CREMA-D: Crowd-sourced emotional multimodal actors dataset // IEEE Transactions on Affective Computing. 2014. V. 5. N 4. P. 377–390. https://doi.org/10.1109/TAFFC.2014.2336244</mixed-citation><mixed-citation xml:lang="en">Cao H., Cooper D.G., Keutmann M.K., Gur R.C., Nenkova A., Verma R. CREMA-D: Crowd-sourced emotional multimodal actors dataset // IEEE Transactions on Affective Computing. 2014. V. 5. N 4. P. 377–390. https://doi.org/10.1109/TAFFC.2014.2336244</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Challenges in Representation Learning Facial Expression Recognition Challenge [Электронный ресурс]. URL: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge (дата обращения: 13.11.2021).</mixed-citation><mixed-citation xml:lang="en">Challenges in Representation Learning Facial Expression Recognition Challenge [Электронный ресурс]. URL: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge (дата обращения: 13.11.2021).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
