Browsing by Author "Rocha , Ricardo Gomes da"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- FullExpression - Emotion Recognition SoftwarePublication . Rocha , Ricardo Gomes da; Pereira, Isabel Cecília Correia da Silva Praça GomesDuring human evolution emotion expression became an important social tool that contributed to the complexification of societies. Human-computer interaction is commonly present in our daily life, and the industry is struggling for solutions that can analyze human emotions, in an attempt to provide better experiences. The purpose of this study was to understand if a software built using the transfer-learning technique on a deep learning model was capable of classifying human emotions, through facial expression analysis. A Convolutional Neuronal Network model was trained and used in a web application, which is available online. Several tools were created to facilitate the software development process, including the training and validation processes, and these are also available online. The data was collected after the combination of several facial expression emotion databases, such as KDEF_AKDEF, TFEID, Face_Place and jaffe. Software evaluation reveled an accuracy in identifying the correct emotions close to 80%. In addition, a comparison between the software and preliminary data from human’s performance, on recognizing facial expressed emotions, suggested that the software performed better. This work can be useful in many different domains such as marketing (to understand the effect of marketing campaigns on people’s emotional states), health (to help mental diseases diagnosis) and industry 4.0 (to create a better collaborating environment between humans and machines).