Measuring human emotions with modular NNS and computer vision based applications
Închide
Articolul precedent
Articolul urmator
379 2
Ultima descărcare din IBN:
2022-03-30 22:18
SM ISO690:2012
ALBU, Veaceslav. Measuring human emotions with modular NNS and computer vision based applications. In: Tendinţe contemporane ale dezvoltării ştiinţei: viziuni ale tinerilor cercetători. 10 martie 2015, Chișinău. Chișinău, Republica Moldova: Universitatea Academiei de Ştiinţe a Moldovei, 2015, p. 14.
EXPORT metadate:
Google Scholar
Crossref
CERIF

DataCite
Dublin Core
Tendinţe contemporane ale dezvoltării ştiinţei: viziuni ale tinerilor cercetători 2015
Conferința "Tendinţe contemporane ale dezvoltării ştiinţei: viziuni ale tinerilor cercetători"
Chișinău, Moldova, 10 martie 2015

Measuring human emotions with modular NNS and computer vision based applications


Pag. 14-14

Albu Veaceslav
 
Institutul de Matematică şi Informatică al AŞM
 
Disponibil în IBN: 13 februarie 2019



Teza

One of the most prominent innovations in the research world in the past decade is the introduction of neuroscience and computer vision based applications to measuring human emotions. The aim of this research is to provide statistical observations and measurements of human emotional states in a chosen environment. Using computer vision and machine learning algorithms, emotional states of multiple targets can be inferred from facial expressions recorded visually by a camera. In this research, emotions are recorded, recognized, and analyzed to give statistical feedback of the overall emotions of a number of targets within a certain time frame. This feedback can provide important measures for user response to a chosen system. We propose a hybrid architecture for complex event analysis and forecasting. The real-time analysis of emotions (facial expression and pulse analysis) is performed with the help of state-of-the art biometric techniques [1, 2], such as Kinect data analysis. We suggest using modular neural network architecture for time series analysis and predictions, based on the statistical data combined with the biometric measurements. The natural application of the proposed architecture is collecting data for marketing purposes: analysis of customer behaviour, estimation of client’s reaction on advertisement products etc.