Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
DYNA
Print version ISSN 0012-7353
Abstract
MONSALVE-PULIDO, Julián Alberto and PARRA-RODRIGUEZ, Carlos Alberto. Characterization of postures to analyze people’s emotions using Kinect technology. Dyna rev.fac.nac.minas [online]. 2018, vol.85, n.205, pp.256-263. ISSN 0012-7353. https://doi.org/10.15446/dyna.v85n205.69470.
This article synthesizes the research undertaken into the use of classification techniques that characterize people's positions, the objective being to identify emotions (astonishment, anger, happiness and sadness). We used a three-phase exploratory research methodology, which resulted in technological appropriation and a model that classified people’s emotions (in standing position) using the Kinect Skeletal Tracking algorithm, which is a free software. We proposed a feature vector for pattern recognition using classification techniques such as SVM, KNN, and Bayesian Networks for 17,882 pieces of data that were obtained in a 14-person training sample. As a result, we found that that the KNN algorithm has a maximum effectiveness of 89.0466%, which surpasses the other selected algorithms.
Keywords : analysis of emotions; recognition of postures; free software; Kinect, KNN.