A deep learning approach for facial emotions recognition using principal component analysis and neural network techniques
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18470%2F22%3A50020172" target="_blank" >RIV/62690094:18470/22:50020172 - isvavai.cz</a>
Result on the web
<a href="https://onlinelibrary.wiley.com/doi/epdf/10.1111/phor.12426" target="_blank" >https://onlinelibrary.wiley.com/doi/epdf/10.1111/phor.12426</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1111/phor.12426" target="_blank" >10.1111/phor.12426</a>
Alternative languages
Result language
angličtina
Original language name
A deep learning approach for facial emotions recognition using principal component analysis and neural network techniques
Original language description
In this work, advanced facial emotions are recognized using Neural network-based (NN) PCA methodology. The earlier models are cannot detect facial emotions with moving conditions but the CCTV and other advanced applications are mostly depending on moving object-based emotion recognition. The blurring, mask, and moving object-based facial image are applied to the training process, and at the testing condition, real-time facial images are applied. The PCA is extracting features and pre-processing the images with NN deep learning process. The proposed facial emotion recognition model is most useful for advanced applications. The design is finally verified through confusion matrix computations and gets measures like accuracy 98.34%, sensitivity 98.34% Recall 97.34%, and F score 98.45%. These output results compete with present models and outperformance the methodology.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
PHOTOGRAMMETRIC RECORD
ISSN
0031-868X
e-ISSN
1477-9730
Volume of the periodical
37
Issue of the periodical within the volume
180
Country of publishing house
NL - THE KINGDOM OF THE NETHERLANDS
Number of pages
18
Pages from-to
435-452
UT code for WoS article
000888531500001
EID of the result in the Scopus database
2-s2.0-85143389375