Design a System for Hand Gesture Recognition with Neural Network

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 02 | Feb 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1088
Design a System for Hand Gesture Recognition with Neural Network
Vaishali M. Gulhane1, Dr. Amol Kumbhare2
1Student inElectronics & Communication Dept., Dr. A.P.J.Abdul Kalam University, Ind withore /MP/India
2Asso. prof. in Electronics Department, Dr. A.P.J.Abdul Kalam University, Indore /MP/India
---------------------------------------------------------------------------***---------------------------------------------------------------------------
ABSTRACT: The intellectual computing of an effective human-
computer interaction (HCI) or human alternative and
augmentative communication (HAAC) is vital in our lives in
today's technological environment. One of the most essential
approaches for developing a gesture-based interface system for
HCI or HAAC applications is hand gesture recognition. As a
result, in order to create an advanced hand gesture recognition
system with successful applications, it is required to establish
an appropriate gesture recognition technique. Human activity
and gesture detection are crucial components of the rapidly
expanding area of ambient intelligence, which includes
applications such as robots, smart homes, assistive systems,
virtual reality, and so on. We proposed a method for
recognizing hand movements using surface electromyography
based on an ANN. The CapgMyo dataset based on the Myo
wristband (an eight-channel sEMG device) is utilized to assess
participants' forearm sEMG signals in our technique. The
original sEMG signal is preprocessed to remove noise and
detect muscle activity areas, then signals are subjected to time
and frequency-based domain feature extraction. We used an
ANN classification model to predict various gesture output
classes for categorization. Finally, we put the suggested model
to the test to see if it could recognize these movements, and it
did so with an accuracy of 87.32 percent.
Keywords—Hand Gesture Recognition, Human Computer
Interaction, Electromyography, Artificial Neural
Networks.
I. INTRODUCTION
Human computer interaction (HCI) or human alternative and
augmentative communication (HAAC) is becoming
increasingly essential in our daily lives in the current
intelligent computing environment. One of the most
important research techniques in HCI or HAAC applications is
gesture recognition. Gestures are communicative, meaningful
body motions or body language expressions that involve
physical actions of the fingers, hands, arms, face, head, or
torso with the aim of transmitting meaningful information or
engaging with the environment in general. Hands are utilized
to perform the majority of essential body language
expressions since they are more flexible and controlled
elements of the human body. As a result, hand gestures are
appropriate for communicating information such as
expressing a sentiment, indicating a number, pointing out an
object, and so on. Sign language and gesture-based computer
control both employ hand gestures as a main interface
method [1]. [7]. Simple mechanical devices such as a
keyboard and mouse are utilized for man-machine
interaction in a conventional HCI system. These gadgets, on
the other hand, limit the pace and spontaneity with which
man and machine communicate. On the other hand, due to its
natural interaction ability, interaction methods based on
hand gestures and computer vision have become a popular
alternative communication modality for man-machine
contact in recent years. For successful HCI or HAAC
applications such as robots, sign language communication,
virtual reality, and so on, a proper design of hand gesture
recognition framework may be utilized to build an advanced
hand gesture-based interface system. The method of
recognizing the movements made by a human hand or hands
is known as hand gesture recognition [13].
Because hand gestures vary in time and location, as
well as across ethnic backgrounds, it's nearly difficult to
identify any single one. Any gesture, broadly defined, is a
deliberate hand movement that involves movements of the
fingers, palm, and wrist to communicate information. When
employed to generate a range of postures or motions,
gestures are regarded to extend to the arms as well as the
hands in the field of gesture recognition. A computer or other
machine that detects human gestures is one that can be
operated efficiently using the user's hands and arms. Because
gestures come easily to humans and are an essential element
of how we communicate, using gestures for human-computer
interactions is a simple process. Users should be able to
instruct computers to perform complicated activities using
only a single posture or a few basic, continuous, dynamic
hand gestures [23]. Hand gesture recognition technologies
are divided into two groups depending on sensing
techniques: (i) gloves, sensor, or wearable band-based
approaches, and (ii) vision-based techniques.
EMG signals are used in a variety of applications,
including neuromuscular illness diagnosis,
prosthetic/orthotic device control, human-machine
interfaces, virtual reality gaming, and the creation of muscle-
oriented exercise equipment. EMG signals have been used in
a variety of research projects to interface with machines and
computers. The goal of gesture recognition research is to
develop a system that can recognize distinct human gestures

and utilize them to communicate information or control
devices [4] [6] [8] [14]. Gestures can come from
anybodyaction or state, although they are most often made
with the hands or the face. EMG signals, which are used to
assess muscle activity, are used to record hand movements.
The development of EMG-based control has gotten a lot of
attention in the last three decades since it will improve the
social acceptability of handicapped and elderly people by
enhancing their quality of life. However, pattern identification
of EMG data is the most difficult element of designing
myoelectric control-based interfaces [21] [30]. This is due to
substantial differences in EMG signals, which have various
characteristics based on age, muscle activity, motor unit
pathways, skin-fat layer, and gesture style. EMG signals
include more complex kinds of noise than other bio signals,
which are generated by intrinsic equipment and ambient
noise, electromagnetic radiation, motion artefacts, and the
interaction of various tissues. It might be difficult to extract
valuable characteristics from an amputee's or handicapped
person's remaining muscles. When dealing with a multiclass
classification problem, this problem becomes even more
complex to solve. Many studies have explored various types
of EMG signal categorization techniques with satisfactory
recognition results. The goal of this study is to create a
system architecture that can detect hand movements that
communicate specific information utilizing an EMG signal.
The following is a breakdown of the paper's
structure. The work of several researchers on the
categorization of the EMG signal is discussed in section II. The
suggested technique is presented in Section III, which
includes signal processing, namely segmentation, feature
extraction, and classification. In part IV, the findings are
examined, and in section V, the conclusion is presented.
II. RELATED WORK
The majority of the studies utilized hand gesture
recognition methods that may be divided into two categories:
i) glove, sensor, or wearable band-based techniques, and ii)
vision-based techniques, all of which are detailed below.
P N Huu et al. [1] researched, surveyed, and performed
research in order to give an overview of human hand
gesture recognition, covering the main processes of hand
gesture recognition, as well as the most often used approach
and methodology. A convolutional neural network-based
gesture recognition technique is presented, in which training
and testing are carried out with various convolutional neural
networks, as opposed to other known methods and designs
[2]. For the problem of dynamic hand gesture detection, an
efficient strategy for utilizing knowledge from various
modalities in training unimodal 3D convolutional neural
networks (3D-CNNs) is described [3]. A. Chahid and
colleagues [4] devised a technique. The Quantization-based
position Weight Matrix (QuPWM) feature extraction
approach for multiclass classification to improve the
interpretation of biomedical signals has shown promise in
extracting important features from a variety of biomedical
signals, including EEG and MEG signals. A technique [5] was
suggested to categorize hand motions by one smartphone
utilizing inaudible high-frequency sound, and the model
classified 8 hand gestures with 94.25 percent accuracy. A.
Devaraj et al. [6] utilized SVM and KNN machine learning
classifiers to recognize a specific hand motion from an EMG
signal recorded by a sensor-based band. B. Besma et al. [7]
presented a method for identifying two movements (wrist
flexion and wrist extension) by decoding surface
electromyography (EMG) signals of amputees, which has
proved to have an overall accuracy of about 80% and may be
utilized for prosthesis. A comparison is presented between
the created band and the Myo Armband, which recognizes
gestures using surface-Electromyography (s-EMG) [8]. Based
on spatio-temporal characteristics such as Histogram of
Oriented Gradients 3DHOG and Histogram of Oriented Optical
Flow 3DHOOF, a gesture recognition system was described
[9]. [10] suggested an effective deep convolutional neural
networks technique for hand gesture detection that used
transfer learning to overcome the need of a big labelled
dataset.
The area under the ROC curve metric achieved 98
percent overall performance using a machine learning
technique developed [11] for real-time identification of 16
movements of user hands using the Kinect sensor that
respects such constraints. Hand movements and finger
detection in still pictures and video sequences are the subject
of T. Bravenec et al. [12]. Using a wrist-mounted tri-axial
accelerometer, a computational solution for human-robot
interaction was given [13]. Surface electromyography was
used to identify hand movements using a technique based on
support vector machines (SVM) [14]. (sEMG). A model [15]
for real-time hand gesture identification that takes as input
electromyography (EMG) data recorded on the forearm and
uses an auto-encoder for automated feature extraction and an
artificial feed-forward neural network for classification,
utilizing the commercial sensor Myo Armband. A novel 3D
hand gesture identification technique [16] is based on a deep
learning model in which sequences of hand-skeletal joint
locations are analyzed by parallel convolutions in a new
Convolutional Neural Network (CNN). Experimental results
are consistent with theoretical estimates and illustrate the
benefits of the suggested gesture recognition system design
[17], which utilizes a hand detector to identify hands in the
frame and then switches to a gesture classifier if a hand is
found. A hand gesture recognition solution based on LSTM-
RNNs and 3D Skeleton Features [18] presents, with

experimental results showing that the suggested technique
has a resilience of 92.196 percent on a self-defined dataset.
The use of the temporal inter-frame pattern on the
identification of both static and dynamic hand gestures is
explored in a three-level system [19]. A sensor-based system
that deciphers this sign language of hand gestures for English
alphabets has been created [20].
A hand gesture identification model [21] developed that
used surface electromyography in the transient state, support
vector machines (SVM), and discrete wavelet transforms to
recognize hand motions that lasted a brief period (i.e., short-
term gestures) (DWT). Author [22] has provided a successful
dynamic hand gesture and movement trajectory recognition
system that may be utilized in real-time for effective HRI
interaction. E. Kaya et al. [23] developed a hand gesture
recognition method based on surface electromyography
(EMG) signals collected from a wearable device, the Myo
armband, to classify and recognize numbers from 0 to 9 in
Turkish Sign Language. To recognize the hand gestures, they
used machine learning techniques such as kNN, SVM, and
ANN. The suggested approach by J. Kim et al. [24] transforms
reflected and recorded sound data into an image in a short
time using a short time Fourier transform, and then applies
the acquired data to a convolutional neural network (CNN)
model to identify hand motions. On three datasets, a neural
network design consisting of two types of recurrent neural
network (RNN) cells was built [25], revealing that this very
modest network beats state-of-the-art hand gesture
identification techniques that depend on multi-modal data by
a wide margin. K. N. Krisandria et al. [26] use hand motions to
create interactions between humans and computers, which
are recognized by the palm of the hand, which is derived from
the findings of human skeletal segmentation using the Kinect
camera. The framework combines incoming signals [27] at
the semantic level, a method similar to that used in multi-
agent systems, where modals give local semantics before
entering the fusion module. A novel human hand gesture
dataset is given, which was collected using a low-cost,
wearable IoT-based device with accelerometer and gyroscope
sensors. A real-time hand gesture recognition accelerator
based on hand skeleton extraction has been suggested
surface electromyography (sEMG) was collected from six
hand and forearm muscles and categorized using three
distinct techniques.
III. PROPOSED WORK
Process, analyze, and recognize the hand gesture signal is
the goal of the EMG-based hand gesture recognition system.
The whole process of a hand gesture recognition system may
be broken down into two phases: training and testing. Figure
1 shows a schematic representation of a hand gesture
recognition system. The preprocessing, feature extraction,
and feature selection processes are the same in both the
training and testing phases. Preprocessing, feature extraction,
feature reduction, and classification are the phases of a hand
gesture recognition system in general.
Fig 1: The schematic diagram of a hand gesture recognition
system
1. Hand Gesture Dataset
The CapgMyo is a benchmark database of high-density
sEMG (HD-sEMG) recordings of diverse participants' hand
gestures, based on an 8x16 electrode array and an acquisition
equipment as illustrated in fig 2.
Fig 2: Original surface electromyography (sEMG) signals
recorded by the MYO armband.

2. Preprocessing
Because of its sensitivity, EMG signals are often polluted
by external noise sources and artefacts. Using these tainted
signals will also result in a poor classification result, which is
undesirable. Electrode noise, motion artefacts, power line
noise, ambient noise, and intrinsic noise in electrical and
electronic equipment are the most common sources of noise,
artefacts, and interference that can contaminate EMG signals.
The first three forms of noise can be removed by employing
standard filtering techniques such as a band pass filter or a
band-stop filter, or by utilizing high-quality equipment with
correct electrode placement. Other noises/artifacts and
interferences of random noise that are in between the main
frequency range of EMG are difficult to eliminate.
Wavelet-based approaches are useful for studying many
forms of non-stationary data, such as EMG. For example, the
Discrete Wavelet Transform (DWT) scales and shifts the
mother wavelet and decomposes a discrete-time signal x[k]
into a collection of signals. Finding the appropriate number of
wavelet decomposition levels is the first step in the DWT
decomposition. At the same time, the signal x[k] passes
through the high-pass and low-pass filters. In wavelet
decomposition, detail (D) represents the signal at high
frequency, while approximation (A) represents the low-
frequency component (A). The similarity between the signal
and the wavelet functions is measured by these coefficients.
After down sampling the resultant filtered signal by two, this
procedure is repeated on the low pass approximation
coefficients obtained at each level. This research focuses on
frequency decomposition levels. At each decomposition level
of the DWT, the resulting detailed coefficients reflect distinct
frequency bands of the EMG signals. In this experiment, we
discovered that DWT with DB wavelet provided the best
results. Wavelet-based feature extraction methods create a
vector that is far too large to be utilized as a classifier input.
This approach reduces the amount of characteristics that may
be extracted from wavelet coefficients. The chosen
characteristics of EMG signals are extracted using DWT. After
obtaining DWT coefficients, statistical characteristics for each
of the five DWT sub-bands are retrieved.
3. Features Extraction and Selection
Because of the complexity of EMG signals, effective
feature selection is critical for successful classification. The
characteristics utilized to represent the raw EMG signals have
a huge impact on the pattern classification system's
performance. Because it is difficult to extract a feature
parameter that completely reflects the unique characteristic
of the recorded EMG signals to a motion instruction, many
feature parameters are required for EMG signal
categorization. For the categorization of EMG signals,
traditional characteristics derived from the time domain,
frequency domain, time-frequency domain, and time-scale
domain are used. After wavelet transformation or 3 level DB
decomposition of signal, we employed hand created, that is,
manually derived features in the time and frequency domain.
Mean absolute value (MAV), waveform length (WL), zero
crossings (ZC), slope sign changes (SSC), RMS, and standard
deviation are all assessed in the time domain. Skewness,
mean frequency, and kurtosis are all terms used in the
frequency domain.
4. Classification (train, validate and test)
After collecting feature dataset for train and test with its
corresponding output labels, hand gesture classification was
done using Artificial Neural Network via train, validate, and
test stages to produce anticipated output as hand gesture.
The ANN employed in this study is a dynamic and strong
back-propagation (BP) type network. Its state evolves over
time until it reaches the final equilibrium point, which is
attained by successful training. The Widrow-Hoff learning
rule is applied to a multiple-layer network with a nonlinear
differentiable transfer function to generate BP. The learning
rule for neural network propagation determines how the
weights between the layers change. ANN in which hidden
layer, activation function, epoch, error rate, and learning rate
are utilized as hyper parameters to adjust or train the
classifier for the optimal validation of the training process.
Where the training data has already been labelled, the
classifiers from the supervised learning model are utilized. In
machine learning, there are many different types of
categorization algorithms. The Multi-Layer Perceptron (MLP)
Artificial Neural Network (ANN) based on the Levenberg–
Marquardt algorithm is used for classification in this study
since it is a robust approach in this particular instance.
According to the literature, the accuracy of an artificial neural
network's classification depends on the feature set, network
topology, and training technique chosen. A series of input and
output units linked together to form a network is what an
ANN is. There are three layers in the network: an input layer,
a tan-sigmoid hidden layer, and a linear output layer. The
advantages of neural networks are primarily their high
tolerance for noisy input and their ability to classify
untrained patterns. They might also be beneficial if there isn't
enough information about the relationships between
characteristics and classes. Hidden layers and output layer
nodes were activated using a hyperbolic tangent sigmoid
function and a linear function, respectively. The acquired
characteristics of sEMG signals are fed into the ANN, and the
network output is the categorization, or the estimated
movement caused. The network's overall diagram is depicted
in Fig.5.

Fig 3: General Architecture of Artificial Neural Network
The hidden layer size is an essential parameter for ANN,
since it adds to network accuracy. The weights linking the
hidden layer to the output get smaller as the number of
neurons in the hidden layer grows. Increasing this value
typically increases the network's training performance, but it
doesn't always assist with generalization. Under-fitting
occurs when a network's weight and biases are improperly
adjusted during training due to the use of a small number of
neurons in the hidden layers. If the number of hidden
neurons is increased beyond a certain point, the network's
accuracy may suffer. To save a high number of network
variables, it is preferable to have a lot of memory, thus the
training process becomes complicated. The right number of
neurons in the hidden layer is chosen to balance the
network's efficiency and complexity. The number of neurons
in a neural network is not determined by a rule of thumb. For
the selection of neurons in the neural network in this study, a
trial-and-error technique is employed. To minimize
overfitting, the training input data were randomly separated
into three sets, with 70% of the samples assigned to the
training set, 15% to the validation set, and 15% to the test
set. To explore the influence of hidden layer size on class
estimation accuracy, we raised the number of neurons from 1
to 15. Under-fitting is shown in neural networks with 1
hidden neuron, while over-fitting is seen in neural networks
with 15 hidden neurons, with 5 being the ideal number of
hidden neurons. In the input layer, four neurons correspond
to the input feature, while two neurons in the output layer
represent the two classes. During training, the back-
propagation method is used to modify the weights and biases
while reducing the difference between the goal and neural
network output.
More information isn't necessarily better in machine
learning applications, as feature selection approaches
demonstrate. Following the feature extraction procedure, it
was discovered that a specific collection of features may
impair or provide no value to the classifier's performance.
Counting the number of times, a feature divides a tree can be
a useful metric for feature selection.
IV. RESULTS AND DISCUSSION
In this experimentation, we used MATLAB R2018b to
construct a recommended architecture to assess the
proposed model. On a desktop computer with an Intel®
CoreTM i5 CPU and 8GB of RAM, the suggested model was
tested. The CapgMyo dataset is a benchmark collection of
high-density sEMG (HD-sEMG) recordings of hand gestures
made by diverse individuals (able-bodied people ranging in
age from 23 to 26 years) utilizing an 8x16 electrode array and
a newly built acquisition equipment. We employed eight
distinct hand motions in this project, as shown in Fig. 4. Each
move was performed 10 times and held for 3 to 10 seconds
each time (10 trials).
Fig 4: The used eight hand gestures from CapgMyo Dataset
[22].
The performance of the classifier model is described
using a confusion matrix also called error matrix. It's a matrix
in which each row represents examples from an actual class
and each column represents instances from a predicted class,
or vice versa. The confusion matrix is used to evaluate the
performance using the accuracy, sensitivity, and specificity
criteria.
𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦=(𝑇𝑃+𝑇𝑁)/(𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁)
𝑆ensitivity=𝑇𝑃/(𝑇𝑃+𝐹𝑁)

𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦= 𝑇𝑁/(𝑇𝑁+𝐹𝑃)
Were, TP – true positive, TN – true negative, FP – false
positive, FN – false negative
Fig 5: Decomposition of test signal using DWT
Figure 5 displays a sample of the test signal waveform after
discrete wavelet transformation preprocessing (DWT).
Training, validation, and testing are the three steps of our
system's evaluation. 70% of the data samples are utilized in
the training and validation phases, whereas 30% are used in
the testing phase. After the train data has been validated, test
samples are analyzed to determine the proper hand gesture
as a projected output. Table 1 lists the parameters that were
assessed for testing and compares them to existing
techniques used by researchers, also graphically compared in
fig. 6.
Table 1: Comparative Results
Parameters Results (%)
Ref [7] Ref
[31]
Ref
[32]
Proposed
Method
Accuracy 81.25 83.1 86.0 87.32
Sensitivity 70.48 - - 75.44
Specificity 59.72 - - 70.35
Fig 6: comparative result performance.
V. CONCLUSION
This paper provided a hand gesture detection algorithm
based on CapgMyo datasets from the Myo armband device.
The approach first preprocesses the data before extracting
features from it using temporal and frequency domain
statistics. Finally, utilizing 70% of the dataset feature vectors,
an artificial neural network with feed forward
backpropagation network is used to create a classifier. In this
experiment, we test the remaining 30% of feature vectors.
Instead of merely obtaining the results recognized by any
gesture, every test feature vectors must be categorized by a
classifier so that each feature vector may be recognized
correctly. A feature vector is classed as no gesture if it is not
detected. Our suggested model has an accuracy of 87.32
percent, which is greater than existing approaches. In the
future, we'll try to implement the approach in a real-time
application. Based on the outcomes of this study, it is clear
that PPG can provide similar HGR results as s-EMG.
VI. REFERENCES
[1] P. N. Huu and H. L. The, "Proposing Recognition
Algorithms For Hand Gestures Based On Machine
Learning Model," 2019 19th International Symposium
on Communications and Information Technologies
81.25 83.1 86 87.32
70.48
0 0
75.44
59.72
0 0
70.35
0
10
20
30
40
50
60
70
80
90
100
Ref [7] Ref [31] Ref [32] Proposed
Method
Results (%)
Comparative Performance
Accuracy Sensitivity Specificity

(ISCIT), Ho Chi Minh City, Vietnam, 2019, pp. 496-501,
doi: 10.1109/ISCIT.2019.8905194.
[2] Pinto, Raimundo& Braga Borges, Carlos & Almeida,
Antonio & Paula Jr, Ialis, “Static Hand Gesture
Recognition Based on Convolutional Neural Networks,”
2019 Journal of Electrical and Computer Engineering.
pp. 1-12. doi: 10.1155/2019/4167890.
[3] M. Abavisani, H. R. V. Joze and V. M. Patel, "Improving
the Performance of Unimodal Dynamic Hand-Gesture
Recognition With Multimodal Training," 2019
IEEE/CVF Conference on Computer Vision and Pattern
Recognition (CVPR), Long Beach, CA, USA, 2019, pp.
1165-1174, doi: 10.1109/CVPR.2019.00126.
[4] A. Chahid, R. Khushaba, A. Al-Jumaily and T. -M. Laleg-
Kirati, "A Position Weight Matrix Feature Extraction
Algorithm Improves Hand Gesture Recognition," 2020
42nd Annual International Conference of the IEEE
Engineering in Medicine & Biology Society (EMBC),
Montreal, QC, Canada, 2020, pp. 5765-5768, doi:
10.1109/EMBC44109.2020.9176097.
[5] J. Cheon and S. Choi, "Hand Gesture Classification based
on Short-Time Fourier Transform of Inaudible Sound,"
2020 International Conference on Artificial Intelligence
in Information and Communication (ICAIIC), Fukuoka,
Japan, 2020, pp. 472-475, doi:
10.1109/ICAIIC48513.2020.9065201.
[6] A. Devaraj and A. K. Nair, "Hand Gesture Signal
Classification using Machine Learning," 2020
International Conference on Communication and Signal
Processing (ICCSP), Chennai, India, 2020, pp. 0390-
0394, doi: 10.1109/ICCSP48568.2020.9182045.
[7] B. Besma, K. Malika, Z. Hadjer, B. Yasmina, A. Sarra and
E. Hammoudi, "Development of an Electromyography-
Based Hand Gesture Recognition System for Upper
Extremity Prostheses," 2019 6th International
Conference on Image and Signal Processing and their
Applications (ISPA), Mostaganem, Algeria, 2019, pp. 1-
6, doi: 10.1109/ISPA48434.2019.8966886.
[8] K. Subramanian, C. Savur and F. Sahin, "Using
Photoplethysmography for Simple Hand Gesture
Recognition," 2020 IEEE 15th International Conference
of System of Systems Engineering (SoSE), Budapest,
Hungary, 2020, pp. 307-312, doi:
10.1109/SoSE50414.2020.9130489.
[9] S. e. Agab and F. z. Chelali, "HOG and HOOF Spatio-
Temporal Descriptors for Gesture Recognition," 2018
International Conference on Signal, Image, Vision and
their Applications (SIVA), Guelma, Algeria, 2018, pp. 1-
7, doi: 10.1109/SIVA.2018.8661127.
[10] M. Al-Hammadi, G. Muhammad, W. Abdul, M.
Alsulaiman, M. A. Bencherif and M. A. Mekhtiche, "Hand
Gesture Recognition for Sign Language Using 3DCNN,"
in IEEE Access, vol. 8, pp. 79491-79509, 2020, doi:
10.1109/ACCESS.2020.2990434.
[11] M. Benmoussa and A. Mahmoudi, "Machine learning for
hand gesture recognition using bag-of-words," 2018
International Conference on Intelligent Systems and
Computer Vision (ISCV), Fez, 2018, pp. 1-7, doi:
10.1109/ISACV.2018.8354082.
[12] T. Bravenec and T. Fryza, "Multiplatform System for
Hand Gesture Recognition," 2019 IEEE International
Symposium on Signal Processing and Information
Technology (ISSPIT), Ajman, United Arab Emirates,
2019, pp. 1-5, doi:
10.1109/ISSPIT47144.2019.9001762.
[13] D. O. Anderez, L. P. Dos Santos, A. Lotfi and S. W.
Yahaya, "Accelerometer-based Hand Gesture
Recognition for Human-Robot Interaction," 2019 IEEE
Symposium Series on Computational Intelligence
(SSCI), Xiamen, China, 2019, pp. 1402-1406, doi:
10.1109/SSCI44817.2019.9003136.
[14] W. Chen and Z. Zhang, "Hand Gesture Recognition using
sEMG Signals Based on Support Vector Machine," 2019
IEEE 8th Joint International Information Technology
and Artificial Intelligence Conference (ITAIC),
Chongqing, China, 2019, pp. 230-234, doi:
10.1109/ITAIC.2019.8785542.
[15] E. A. Chung and M. E. Benalcázar, "Real-Time Hand
Gesture Recognition Model Using Deep Learning
Techniques and EMG Signals," 2019 27th European
Signal Processing Conference (EUSIPCO), A Coruna,
Spain, 2019, pp. 1-5, doi:
10.23919/EUSIPCO.2019.8903136.
[16] G. Devineau, F. Moutarde, W. Xi and J. Yang, "Deep
Learning for Hand Gesture Recognition on Skeletal
Data," 2018 13th IEEE International Conference on
Automatic Face & Gesture Recognition (FG 2018),
Xi'an, 2018, pp. 106-113, doi: 10.1109/FG.2018.00025.
[17] R. Golovanov, D. Vorotnev and D. Kalina, "Combining
Hand Detection and Gesture Recognition Algorithms
for Minimizing Computational Cost," 2020 22th
International Conference on Digital Signal Processing
and its Applications (DSPA), Moscow, Russia, 2020, pp.
1-4, doi: 10.1109/DSPA48919.2020.9213273.
[18] H. Guo, Y. Yang and H. Cai, "Exploiting LSTM-RNNs and
3D Skeleton Features for Hand Gesture Recognition,"
2019 WRC Symposium on Advanced Robotics and
Automation (WRC SARA), Beijing, China, 2019, pp. 322-
327, doi: 10.1109/WRC-SARA.2019.8931937.
[19] K. Hu, L. Yin and T. Wang, "Temporal Interframe
Pattern Analysis for Static and Dynamic Hand Gesture
Recognition," 2019 IEEE International Conference on
Image Processing (ICIP), Taipei, Taiwan, 2019, pp.
3422-3426, doi: 10.1109/ICIP.2019.8803472.
[20] A. B. Jani, N. A. Kotak and A. K. Roy, "Sensor Based Hand
Gesture Recognition System for English Alphabets Used
in Sign Language of Deaf-Mute People," 2018 IEEE

SENSORS, New Delhi, India, 2018, pp. 1-4, doi:
10.1109/ICSENS.2018.8589574.
[21] A. Jaramillo-Yanez, L. Unapanta and M. E. Benalcázar,
"Short-Term Hand Gesture Recognition using
Electromyography in the Transient State, Support
Vector Machines, and Discrete Wavelet Transform,"
2019 IEEE Latin American Conference on
Computational Intelligence (LA-CCI), Guayaquil,
Ecuador, 2019, pp. 1-6, doi: 10.1109/LA-
CCI47412.2019.9036757.
[22] R. Kabir, N. Ahmed, N. Roy and M. R. Islam, "A Novel
Dynamic Hand Gesture and Movement Trajectory
Recognition model for Non-Touch HRI Interface," 2019
IEEE Eurasia Conference on IOT, Communication and
Engineering (ECICE), Yunlin, Taiwan, 2019, pp. 505-
508, doi: 10.1109/ECICE47484.2019.8942691.
[23] E. Kaya and T. Kumbasar, "Hand Gesture Recognition
Systems with the Wearable Myo Armband," 2018 6th
International Conference on Control Engineering &
Information Technology (CEIT), Istanbul, Turkey, 2018,
pp. 1-6, doi: 10.1109/CEIT.2018.8751927.
[24] J. Kim, J. Cheon and S. Choi, "Hand Gesture
Classification using Non-Audible Sound," 2019
Eleventh International Conference on Ubiquitous and
Future Networks (ICUFN), Zagreb, Croatia, 2019, pp.
729-731, doi: 10.1109/ICUFN.2019.8806145.
[25] P. Koch, M. Dreier, M. Maass, M. Böhme, H. Phan and A.
Mertins, "A Recurrent Neural Network for Hand
Gesture Recognition based on Accelerometer Data,"
2019 41st Annual International Conference of the IEEE
Engineering in Medicine and Biology Society (EMBC),
Berlin, Germany, 2019, pp. 5088-5091, doi:
10.1109/EMBC.2019.8856844.
[26] K. N. Krisandria, B. S. B. Dewantara and D.
Pramadihanto, "HOG-based Hand Gesture Recognition
Using Kinect," 2019 International Electronics
Symposium (IES), Surabaya, Indonesia, 2019, pp. 254-
259, doi: 10.1109/ELECSYM.2019.8901607.
[27] J. J. Lamug Martinez and S. Senorita Dewanti,
"Multimodal Interfaces: A Study on Speech-Hand
Gesture Recognition," 2019 International Conference
on Information and Communications Technology
(ICOIACT), Yogyakarta, Indonesia, 2019, pp. 196-200,
doi: 10.1109/ICOIACT46704.2019.8938421.

Design a System for Hand Gesture Recognition with Neural Network

More Related Content

Similar to Design a System for Hand Gesture Recognition with Neural Network (20)

More from IRJET Journal (20)

Recently uploaded (20)

Design a System for Hand Gesture Recognition with Neural Network