Modeling and recognition of emotions in manufacturing

• Published in: International journal on interactive design and manufacturing Vol. 16; no. 4; pp. 1357 - 1370
• Main Authors: Bertacchini, Francesca, Bilotta, Eleonora, De Pietro, Michela, Demarco, Francesco, Pantano, Pietro, Scuro, Carmelo
• Format: Journal Article
• Language: English
• Published: Paris Springer Paris 01.12.2022; Springer Nature B.V
• Subjects: Additive manufacturing; Algorithms; Animation; CAE) and Design; Computer-Aided Engineering (CAD; Customization; Design; Digitization; Electronics and Microelectronics; Emotion recognition; Emotions; Engineering; Engineering Design; Industrial Design; Industry 4.0; Instrumentation; Machine learning; Manufacturing; Mechanical Engineering; Modelling; New technology; Original Paper; Programming languages; Python; Simulation; Three dimensional printing; Verbal communication; Workflow; Emotion recognition; Industry 4.0; Parametric modeling; Smart manufacturing
• ISSN: 1955-2513; 1955-2505; 1955-2505
• DOI: 10.1007/s12008-022-01028-3

New consumer needs have led industries to the possibility of creating virtual platforms where users can customize products by creating infinite combinations of different results. This made it possible to expand sales by guaranteeing a wide choice that would satisfy all requests. The dynamic and flexible evolution of factories is guaranteed by the introduction of new technologies such as robotization and 3D printers, recognized as two of the pillars of Industry 4.0. The main aim of this paper is to achieve a workflow for the creation and implementation of personalised jewellery based on faces with different emotional expressions. To date, there are few works in the literature investigating the intersection between smart manufacturing and emotion recognition, and these are mainly related to improving human–machine interaction. The authors’ aim is to research for innovation in the intersection of three different fields of study such as parametric modelling, smart manufacturing and emotion recognition in order to create personalized and innovative manufacturable models. To this purpose, an application has been generated that exploits both visual scripting, typical of parametric modelling, and scripting, in the Python programming language. The generated algorithm implements a machine learning for emotion recognition that identifies the label of each user-generated face, validating the effectiveness of the method.