Publication: Preliminary Experiment on Emotion Detection in Illustrations Using Convolutional Neural Network
Дата
2021
Авторы
Journal Title
Journal ISSN
Volume Title
Издатель
Аннотация
© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.The paper describes an experiment on emotion detection in images, specifically illustrations and cartoon images. Usually, detection and classification of emotions are performed on human faces so the algorithm can learn, for example, what a “happy human face” looks like. These algorithms probably can’t transfer their understanding of happiness features onto different types of objects, like animals or cartoon illustrations. We, humans, can recognize and detect signs of emotions (although maybe falsely) in new and unusual objects. Developing an algorithm capable of recognizing emotions in objects it wasn’t trained on would allow for better human-like robots and systems. This is a preliminary study on how well knowledge gained by a typical neural network detection system on a set of objects transfers to new, unknown objects. The neural network detection system used in this study is YOLO. We collected small training datasets using cartoon illustrations of several animals of two categories: happy and sad. We tested the trained network on a set of illustrations depicting a different animal the network hasn’t seen in training. The best performance achieved is 0.69 F1-score.
Описание
Ключевые слова
Цитирование
Shtanko, A. Preliminary Experiment on Emotion Detection in Illustrations Using Convolutional Neural Network / Shtanko, A., Kulik, S. // Advances in Intelligent Systems and Computing. - 2021. - 1310. - P. 490-494. - 10.1007/978-3-030-65596-9_59