2016 IEEE Region 10 Symposium (TENSYMP) 2016
DOI: 10.1109/tenconspring.2016.7519396
|View full text |Cite
|
Sign up to set email alerts
|

Detection and analysis model for grammatical facial expressions in sign language

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0
2

Year Published

2018
2018
2023
2023

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 5 publications
0
1
0
2
Order By: Relevance
“…In works addressing GFE recognition related to Libra sign language (using a dataset for Brazilian sign language [37]), Bhuvan et al [44] explored various machine learning algorithms (such as the multi-Layer perceptron (MLP) [15], the random forest classifier (RFC) [45], and AdaBoost [46], among others) to recognize nine GFEs. They performed experiments (with the 100 coordinates (x, y, z) corresponding to facial points stored in the aforementioned dataset) under the user-dependent model (when training and prediction of a classifier are performed with the same subjects) to choose the best algorithm for each GFE.…”
Section: State Of the Artmentioning
confidence: 99%
“…In works addressing GFE recognition related to Libra sign language (using a dataset for Brazilian sign language [37]), Bhuvan et al [44] explored various machine learning algorithms (such as the multi-Layer perceptron (MLP) [15], the random forest classifier (RFC) [45], and AdaBoost [46], among others) to recognize nine GFEs. They performed experiments (with the 100 coordinates (x, y, z) corresponding to facial points stored in the aforementioned dataset) under the user-dependent model (when training and prediction of a classifier are performed with the same subjects) to choose the best algorithm for each GFE.…”
Section: State Of the Artmentioning
confidence: 99%
“…Bhuvan et al (2016) investigaram a seleção do algoritmo de aprendizado de máquina com melhor desempenho para cada expressão facial gramatical, tanto para modelos dependentes do usuário quanto para modelo independente do usuário. Após isso, identificaram os principais pontos faciais para detectar cada expressão com o melhor algoritmo de aprendizado de máquina para o modelo independente do usuário.…”
unclassified
“…As medidas tradicionalmente usadas nessaárea, como: F-score, acurácia, curva ROC também são utilizadas nos estudos aqui levantados. No quadro 4 está listado as técnicas e os métodos utilizadas nos estudos Bhuvan et al (2016). realizaram experimentações exaustivas com oito diferentes algoritmos de aprendizado de máquina para detectar nove diferentes tipos de expressões faciais gramaticais modelados como problema de classificação binária diferente para cada expressão.…”
unclassified