eONPUIR

An adaptive convolutional neural network model for human facial expression recognition

Показать сокращенную информацию

dc.contributor.author Arsirii, Olena
dc.contributor.author Арсірій, Олена Олександрівна
dc.contributor.author Petrosiuk, Denys
dc.contributor.author Петросюк, Денис Валерійович
dc.date.accessioned 2023-07-13T21:37:25Z
dc.date.available 2023-07-13T21:37:25Z
dc.date.issued 2023-07-03
dc.identifier.citation Arsirii, O., Petrosiuk, D. (2023). An adaptive convolutional neural network model for human facial expression recognition. Herald of Advanced Information Technology, Vol. 6, N 2, р. 128–138. еn
dc.identifier.citation Arsirii, O. An adaptive convolutional neural network model for human facial expression recognition / O. Arsirii, D. Petrosiuk // Herald of Advanced Information Technology = Вісн. сучас. інформ. технологій. – Оdesa, 2023. – Vol. 6, N 2. – Р. 128–138. еn
dc.identifier.issn 2663-0176
dc.identifier.issn 2663-7731
dc.identifier.uri http://dspace.opu.ua/jspui/handle/123456789/13967
dc.description.abstract The relevance of solving the problem of recognizing facial expressions in the image of a person's face for the formation of a model of social interactions in the development of intelligent systems for computer vision, human-machine interaction, online learning, emotional marketing, and game intelligence is shown. The aim of the work is to reduce the training time and computational resources without losing the reliability of the multivalued classification of motor units for solving the problem of facial expression recognition in a human face image by developing an adaptive model of a convolution neural network and a method for its training with “fine tuning” of parameters. To achieve the goal, several tasks were solved in the work. Models of specialized convolution neural networks and pre-trained on the ImageNet set were investigated. The stages of transfer learning of convolution neural networks were shown. A model of a convolutional neural network and a method for its training were developed to solve the problems of facial expression recognition on a human face image. The reliability of recognition of motor units was analyzed based on the developed adaptive model of a convolution neural network and the method of its transfer learning. It is shown that, on average, the use of the proposed loss function in a fully connected layer of a multi-valued motor unit classifier within the framework of the developed adaptive model of a convolution neural network based on the publicly available MobileNet-v1 and its transfer learning method made it possible to increase the reliability of solving the problem of facial expression recognition in a human face image by 6 % by F1 value estimation. en
dc.language.iso en_US en
dc.publisher Nauka i Tekhnika en
dc.subject Convolution neural networks en
dc.subject facial expression recognition en
dc.subject deep learning en
dc.subject transfer learning en
dc.subject multilabel classification en
dc.title An adaptive convolutional neural network model for human facial expression recognition en
dc.title.alternative Адаптивна модель згорткової нейронної мережі для розпізнавання міміки людини за зображенням обличчя en
dc.type Article en
opu.citation.journal Herald of Advanced Information Technology en
opu.citation.volume 6 en
opu.citation.firstpage 128 en
opu.citation.lastpage 138 en
opu.citation.issue 2 en
opu.staff.id https://orcid.org/0000-0001-8130-9613 en
opu.staff.id https://orcid.org/0000-0003-4644-3678 en


Файлы, содержащиеся в элементе

Этот элемент содержится в следующих коллекциях

Показать сокращенную информацию