2017
DOI: 10.1007/s00521-017-2838-6
|View full text |Cite
|
Sign up to set email alerts
|

Vision-based hand gesture recognition of alphabets, numbers, arithmetic operators and ASCII characters in order to develop a virtual text-entry interface system

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
48
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 44 publications
(48 citation statements)
references
References 23 publications
0
48
0
Order By: Relevance
“…The main reason is that there are too many noise signals in the sample, which greatly increases the difficulty of network identification. A more skillful training strategy is needed to achieve a higher recognition rate [49][50][51]. First of all, four different training methods are used to train the DBNs network with two hidden layers, and the bottom unit of DBNs uses GB_RBM, as shown in Fig.…”
Section: Complex Background Of Gesture Recognition Results and Analysismentioning
confidence: 99%
“…The main reason is that there are too many noise signals in the sample, which greatly increases the difficulty of network identification. A more skillful training strategy is needed to achieve a higher recognition rate [49][50][51]. First of all, four different training methods are used to train the DBNs network with two hidden layers, and the bottom unit of DBNs uses GB_RBM, as shown in Fig.…”
Section: Complex Background Of Gesture Recognition Results and Analysismentioning
confidence: 99%
“…Therefore, the value of λ is experimentally chosen as 5, to give a trade-off between accuracy and speed. Also, experiments show that the tolerance kept at 0.4 gives fairly a good (Misra et al, 2017) at a significantly lower computational cost. Visualizations for successive iterations involved in smoothing of an initially distorted character trajectory is shown in Figure 5.…”
Section: Trajectory Smoothingmentioning
confidence: 96%
“…The focus of this method is mainly on the captured image of gesture; and the extraction of the main features for the recognition process (Kour and Mathew, 2017). The geometrical shape of trajectory and its gesture drawing speed are used to extract different features, which are then used by various pattern recognition algorithms to classify the different gestures (Misra et al, 2017).…”
Section: *Corresponding Authormentioning
confidence: 99%