Soft Computing (2020) 24:15239–15248

https://doi.org/10.1007/s00500-020-04860-5 (0123456789().,-volV)(0123456789().
,- volV)

METHODOLOGIES AND APPLICATION

An efficient method for human hand gesture detection

and recognition using deep learning convolutional neural networks
P. S. Neethu1 • R. Suguna2 • Divya Sathish3

Published online: 23 March 2020

 Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract
The physical movement of the human hand produces gestures, and hand gesture recognition leads to the advancement in
automated vehicle movement system. In this paper, the human hand gestures are detected and recognized using convo-
lutional neural networks (CNN) classification approach. This process flow consists of hand region of interest segmentation
using mask image, fingers segmentation, normalization of segmented finger image and finger recognition using CNN
classifier. The hand region of the image is segmented from the whole image using mask images. The adaptive histogram
equalization method is used as enhancement method for improving the contrast of each pixel in an image. In this paper,
connected component analysis algorithm is used in order to segment the finger tips from hand image. The segmented finger
regions from hand image are given to the CNN classification algorithm which classifies the image into various classes. The
proposed hand gesture detection and recognition methodology using CNN classification approach with enhancement
technique stated in this paper achieves high performance with state-of-the-art methods.

Keywords Hand gesture  Recognition  Mask  Fingers  Segmentation

1 Introduction during the machine is operated (Elmezain et al. 2010; Mitra

and Acharya 2007). Hence, the identification or recognition
At present, human–machine interaction is very important of dynamic gestures is very important than the static ges-
for operating the machines in a remote manner by the tures (Yrk et al. 2006; Tauseef et al. 2009). Initially, the
commands which are received from humans. In this regard, camera, which is connected with machine, captures the
gestures are playing an important role in operating the gestures which are generated by humans. The background
machine at a distant mode (Yasukochi et al. 2008). The of the detected gestures is removed, and the foreground of
machines capture the gestures from the human and recog- the gesture is captured. The noises in the foreground ges-
nize it for operating the machines. The gestures are dif- ture are detected and removed by filtering techniques
ferent types of modes as static and dynamic. The static (Manresa-Yee et al. 2005). These noise removed gestures
gestures do not change their position, while the machine is are compared with pre-stored and trained gestures for
operated, and the dynamic gestures change their positions verifying the sign of the gestures. Figure 1 shows the dif-
ferent types of gestures which are generated by humans.
The automotive sectors and many consumer electronics
Communicated by V. Loia. division use the gesture-based machine operating system
without any human interaction. Besides the static and
& P. S. Neethu dynamic gestures, the gestures of human are also classified
[email protected]
into online and offline gestures. The offline gestures
1
Department of Information and Communication Engineering, operate the icons on the machine, and they are not able to
Anna University, Chennai, India alter the position of the items in the menu or system. The
2
Department of CSE, Vel Tech Rangarajan Dr. Sagunthala online gestures operate the icons in the machine to different
R&D Institute of Science and Technology, Avadi, Chennai, positions or inclinations (Yao and Fu 1935; Liu et al.
India 1898). The online gestures are very much useful in real-
3
Department of CSE, SKR Engineering College, Chennai, time machine operating systems than the offline gestures.
India

123
15240 P. S. Neethu et al.

applied this filtering approach on hand gesture images with

same background. The authors obtained 90.7% of sensi-
tivity, 82.1% of specificity and 87.5% of accuracy. The
main limitation of this approach is that the proposed
algorithm produced optimum results if the background of
the hand gesture image is static. Ashfaq and Khurshid
(2016) used Gabor filtering approach for converting the
spatial domain format hand gesture image into multi-class
domain format image. Then, the authors applied both
Bayesian and Naı̈ve Bayes classifier on Gabor transformed
hand gesture image in order to classify the test hand gesture
image into different classes. The authors obtained high
level of classification accuracy on Naı̈ve Bayes classifier
than the Bayesian classification methodology due to its
simple architecture pattern.
Rahman and Afrin (2013) used support vector machine
Fig. 1 Different hand gesture postures (Kawulok et al. 2012) (SVM) classification approach for classifying the hand ges-
ture images into various classes. The authors achieve 89.6%
Park et al. (2012) and Ren et al. (2013) used Naı̈ve of sensitivity, 79.9% of specificity and 85.7% of accuracy.
Bayes classifier and support vector machine (SVM) The error rate was high in this method, and this is not suit-
methodologies for gesture recognition. These methods did able for fast moving background and foreground object
not support large training dataset, and it also required high images. Rao et al. (2009) developed hand gesture recognition
number of training samples. This drawback is eliminated system using hidden Markov model. The authors constructed
by proposing CNN classifier in this paper. It does not Markov model for foreground fingers in hand gesture image.
require high number of samples in training mode, and the This Markov model was used in both training and testing
complexity level of this algorithm is low. The novelty of modes of binary classification approach. The authors pro-
this proposed work is to implement deep learning algo- duced 90.1% of sensitivity, 82.6% of specificity and 90.6%
rithm in hand gesture recognition system with novel seg- of accuracy. The classification time is high in this method-
mentation technique. ology as the mail limitation.
The paper is organized as follows: Sect. 2 deals the con- The following points are limitations of the conventional
ventional methods of hand gesture recognition, Sect. 3 pro- methods for gesture recognition.
poses CNN classification-based hand gesture recognition, and • Conventional gesture recognition method used SVM
Sect. 4 discusses the simulation results of proposed hand and Naı̈ve Bayes classifier, which required high number
gesture recognition system using Python programming lan- of training samples for gesture pattern recognition.
guage. At the end, Sect. 5 concludes the paper. • The complexities of these algorithms are quite high in
nature.

2 Literature survey

Zuocai Wang et al. (2018) proposed hand gesture recog- 3 Proposed methodology
nition system using particle filtering approach. The authors
applied this filtering approach on hand gesture images with In this paper, the human hand gestures are detected and
same background. The authors obtained 92.1% of sensi- recognized using CNN classification approach. This pro-
tivity, 84.7% of specificity and 90.6% of accuracy. Suguna cess flow consists of hand ROI segmentation using mask
and Neethu (2017) extracted shape features from hand image, fingers segmentation, normalization of segmented
gesture image for the classification of hand gesture images finger image and finger recognition using CNN classifier.
into various classes. Then, these extracted features were Figure 2 shows the proposed flow of hand gesture recog-
trained and classified using k-means clustering algorithm. nition system.
Marium et al. (2017) proposed hand gesture recognition The proposed algorithm for hand gesture recognition
system using convexity algorithm approach. The authors system is given in the following.

123
An efficient method for human hand gesture detection and recognition using deep learning… 15241

Start;

Step 1: Segment hand region ROI using hand mask images;

Step 2: Segment fingers using Connected Component Analysis algorithm;

Step 3: Classify the segmented fingers using CNN classification algorithm;

End;

Fig. 2 Proposed hand gesture

recognition system

3.1 Hand ROI segmentation center pixel of each 3 * 3 patterns is contrast-enhanced by

accumulating the maximum histogram count to the center
The hand region of the image is segmented from the whole pixel. In the case of AHE method, the 3 * 3 patterns are
image using mask images available in open access dataset overlapped with each other and then each center pixel of
(Rautaray and Agrawal 2015). The mask image is inverted, 3 * 3 patterns is contrast-enhanced.
and it is convolved with the hand image which produces Figure 4a shows the different hand gesture images, and
convolved image. The gray-level threshold is applied on Fig. 4b shows the enhanced hand gesture images.
the convolved image which produced hand region seg-
mented image. Figure 3a shows the hand image, and
Fig. 3b shows the mask image.
The parameter recognition rate is important for analyz-
ing the performance of the proposed hand gesture recog-
nition system. The adaptive histogram equalization (AHE)
method (Kapil and Bhattacharya et al. 2016) is used as
enhancement method for improving the contrast of each
pixel in an image. In histogram equalization method, the
entire image region is split into 3 * 3 patterns and the

Fig. 4 a Source hand gesture images and b enhanced hand gesture

Fig. 3 a Hand image and b mask image images

123
15242 P. S. Neethu et al.

3.3 Deep learning convolutional neural network

classifier

The segmented finger regions from hand image are given to

the CNN classification algorithm which classifies the
image into various classes (Hong et al. 2012). This clas-
sification algorithm is explained in the following sections.
Over fitting and back propagation are the present prob-
Fig. 5 Segmented finger region in hand image
lems of neural networks, and hence, it is not able to pro-
duce high classification accuracy for pattern recognition. In
3.2 Fingers segmentation order to overcome such limitations in neural networks,
CNN is used for obtaining high classification accuracy for
In this paper, connected component (CC) analysis algo- hand gesture recognition. CNN has only forward path
rithm is used in order to segment the finger tips from hand which does not have any feedback path for classifications.
image. The finger tip from each hand image is detected and CNN is a kind of deep learning classification methodology
noted as finger peak. The aim of this finger tips segmen- which has many successful records in image analysis and
tation is to count the number of fingers opened in gesture classifications tasks. In this paper, CNN classification
posture. To detect the finger tip in hand image, the m * n methodology is proposed to classify each input hand sign
window is placed over the hand image which starts from gesture image into various classes with high classification
left most and passed over the image toward the right. The accuracy.
value of ‘m’ and ‘n’ is chosen as odd numbers in order to Figure 6 shows the developed CNN architecture which
improve the accuracy of the detection. For each scanning is used in this paper for hand gesture image classifications.
from left to right, the number of ‘1’s is detected and It consists of convolutional filters which perform multi-
counted in window. The number of counted ones is stored plication of kernel with input image (7 * 7 size), pooling
in an array. The number of ones in window is threshold as and fully connected layers as shown in Fig. 6. Figure 7
10. The window scanning is stopped when the count goes shows the detailed internal architecture of proposed CNN
beyond the value of 10. From top to bottom, the region is classifier for hand gesture recognition which depicts con-
marked as finger. Figure 5 shows the segmented finger volution layers and fully connected layers. The fully con-
region in hand image, and the algorithm used for finger nected layers produce N number of output classes.
region segmentation is illustrated in the following The proposed CNN architecture consists of five convo-
algorithm. lutional layers and one fully connected layer with 1024
units. The first convolutional layer is designed with
Gaussian filter of size 3 * 3 for 32 filters, second convo-
lutional layer is designed with Gaussian filter of size 3 * 3
for 64 filters, third convolutional layer is designed with

Inputs: Hand gesture image and m*n window;

Output: Fingers detected image;
Start
Step 1: Move Width (m)* Height (n) window on hand gesture image from the position (i,j) as set
to (0,0);
Step 2: Check its center pixel p(i,j) on m*n window as either 1 or 0;
Step 3: If (p (i,j)==1)
{
Check its neighboring pixel as 1
Set new label ‘a’ if condition is not satisfied;
Else
Set parent label of previous pixel;
}
Else
Step 4: Move m*n window by one pixel towards right;
End

123
An efficient method for human hand gesture detection and recognition using deep learning… 15243

Gaussian filter of size 3 * 3 for 128 filters, fourth convo- feature map have weights that are constrained to be equal;
lutional layer is designed with Gaussian filter of size 3 * 3 however, different feature maps within the same convolu-
for 256 filters, and fifth convolutional layer is designed tional layer have different weights so that several features
with Gaussian filter of size 3 * 3 for 512 filters. The final can be extracted at each location.
fully connected layer is a standard feed forward neural The feature map at ith level can be determined using the
network. This fully connected layer produces final classi- following equation,
fication responses. Yi ¼ f ð W i  I Þ

3.3.1 Convolutional layers where W is internal weight and I is the input source image.

Each convolutional layers act as feature extractors, and 3.3.2 Pooling layers
they extract individual feature set from the input source
image for classification process. The feature map is con- The purpose of the pooling layers is to reduce the spatial
structed by integrating the neuron factors which are resolution of the feature maps which are obtained from
obtained from convolutional layers. All neurons within a convolutional layers. There are two pooling techniques
used in pattern recognition as average pooling and max
pooling, as depicted in Fig. 8. The average pooling
demolishes the originality of the source image pixel, and
the max pooling retains the original pixel value in source
hand gesture image. Hence, in this paper, max pooling
aggregation methodology is used which determines the
maximum value from each feature set map and passes these
maximum feature set values to the next layer. This can be
illustrated in the following equation.
Pi ¼ MaxðYiÞ
In this paper, max pooling with a filter of size 2 9 2
with a stride of 2 is commonly used in practice. This paper
uses 4 numbers of max pooling layers in order to obtain the
optimum classification accuracy.

3.3.3 Fully connected layers

The fully connected layers that follow the convolutional

and pooling layers interpret these feature representations
and perform the function of high-level reasoning.
The first convolutional layer receives training samples
along with test samples. The training set along with test
sample forms the test vector which can be further con-
volved with 3 * 3 mask Gaussian filter for producing its
corresponding hypotheses. Each hypothesis is considered
as new test samples. The second convolutional layer
receives this new test sample along with new training
patters which was produced by the previous convolutional
layer as shown in Fig. 9. The same procedure is followed
until test outcomes received from last convolutional layer.
The output from CNN classification algorithm produces
eight different classes, and each class represents the indi-
vidual hand gesture. Figure 10 shows the training hand
gesture images with different postures and backgrounds.

Fig. 6 Developed CNN architecture used in hand gesture recognition

123
15244 P. S. Neethu et al.

Fig. 7 Internal architecture of proposed CNN classifier for hand gesture recognition

consists of large number of gesture patterns which were

taken at different angles of orientation. The gesture images
in this dataset were obtained or captured with different
background environment under different lighting condi-
tions. In this paper, eight different gestures and 200 images
for each gesture posture are used. These 1600 gesture
images from this open-source dataset are used as training
set in this paper. The testing set contains 800 images which
represent eight different gestures. The hand gesture images
in both training and testing dataset are independent with
each other. This dataset also contains 700 non-hand gesture
images. The following parameters are used to evaluate the
out performance of the proposed work which is stated in
this paper.
SensitivityðSeÞ ¼ TP=ðTP þ FNÞ
SpecificityðSpÞ ¼ TN=ðTN þ FPÞ
Fig. 8 Illustrations of average and max pooling AccuracyðAccÞ ¼ ðTP þ TNÞ=ðTP þ FN þ TN þ FPÞ
Recognition rate ¼ Number of images correctly
4 Results and discussion classified/Total number of images

The proposed hand gesture detection and recognition where TP is the true positive which represents the total
methodology is simulated using Python version 2.7 open- number of correctly recognized hand gesture images (154
source simulation software. This open-source software is images) and TN is the true negative which represents the
authorized by Python scientific distributions. The Python total number of correctly recognized non-hand gesture
software package includes spyder, Anaconda, keras, panda images (50 images). FP is the false positive which repre-
and theano modules. These modules are license free and sents the total number of wrongly recognized hand gesture
available as open tools. Each module is integrated in images (six images), and FN is the false negative which
Python kernel, and Python programming language is used represents the total number of wrongly recognized non-
to simulate the proposed work. The Python software is hand gesture images (five images). The value of sensitivity,
installed in windows 8 with 4 GB internal memory and specificity and accuracy lies between 0 and 100, and they
executed in core i3 processor. are determined in %. Higher values of these parameters
The proposed hand gesture detection and recognition show that the efficiency of the proposed hand gesture
methodology is applied on the images which are openly detection and recognition methodology is high. Table 1
available in Kawulok et al. (2012) dataset. This dataset shows the analysis of recognition rate of proposed method

123
An efficient method for human hand gesture detection and recognition using deep learning… 15245

Fig. 9 Deep learning classification processes

Fig. 10 Training hand gesture

images with different postures
and backgrounds

with respect to different gesture class images and pooling images for different applications. Hence, the CNN classi-
techniques. fication approach is combined with CC algorithm in order
Table 2 shows the performance analysis of proposed to improve the performance of the hand gesture detection
hand gesture recognition method in terms of sensitivity, system. This integrated approach achieved 96.8% of sen-
specificity and accuracy with recognition rate. The pro- sitivity, 89.2% of specificity and 94.8% of accuracy with
posed hand gesture detection and recognition methodology 96.2% of recognition rate.
using CNN classification approach stated in this paper The CNN with CC methodology improved 5.4% of
achieves 96.8% of sensitivity, 89.2% of specificity, 94.8% sensitivity rate from CNN without CC methodology. The
of accuracy and 96.2% of recognition rate. CNN with CC methodology improved 7.8% of specificity
The proposed hand gesture detection methodology is rate from CNN without CC methodology. The CNN with
applied only with CNN classification approach, and this CC methodology improved 3.4% of accuracy rate from
methodology achieved 91.5% of sensitivity, 82.7% of CNN without CC methodology. The CNN with CC
specificity and 91.6% of accuracy with 90.7% of recogni- methodology improved 6% of recognition rate from CNN
tion rate, as stated in Table 2. These simulation results are without CC methodology. The proposed hand gesture
not suitable for real-time recognition of hand gesture recognition system (AHE ? connected component

123
15246 P. S. Neethu et al.

Table 1 Analysis of recognition rate of proposed method with respect Table 4 Analysis of proposed hand gesture detection methodologies
to different gesture class images and pooling techniques using SVM
Gesture Number of Number of Recognition rate (%) Performance SVM Connected AHE ? connected
class gesture gestures correctly analysis classification component component
images recognized Using Using parameters approach analysis ? SVM analysis ? SVM
average max (%) classification classification
polling polling approach approach
Class 1 200 196 98 99 Sensitivity 89.1 90.5 92.1
Class 2 200 195 97.5 98.5 Specificity 78.7 87.5 89.9
Class 3 200 194 97 98.5 Accuracy 87.5 91.6 93.5
Class 4 200 194 97 99 Recognition 88.2 90.5 91.5
Class 5 200 193 96.5 99 rate
Class 6 200 192 96 98.5
Class 7 200 193 96.5 98.5
Class 8 200 193 96.5 98.5 specificity and 93.5% of accuracy with 91.5% of recogni-
1600 1550 96.8 98.7 tion rate, as depicted in Table 4.
The proposed CNN-based hand gesture recognition
system is compared with SVM classifier. The kernel of this
Table 2 Performance analysis of proposed hand gesture recognition SVM classifier is categorized into two types as linear and
method nonlinear. The regression pattern of the linear kernel SVM
Performance analysis parameters Experimental results (%) is exponentially curved than the regression pattern of the
nonlinear kernel SVM classifier. In this paper, the CNN
Sensitivity 98.1
classification results are compared with linear kernel SVM
Specificity 93.4 type.
Accuracy 96.2 Table 5 shows the performance comparisons of pro-
Recognition rate 98.7 posed hand gesture detection and recognition methodology
with state of arts in terms of sensitivity, specificity and
accuracy. The proposed hand gesture detection and
Table 3 Analysis of proposed hand gesture detection methodologies recognition methodology stated in this paper is compared
using CNN
with the conventional methods as Wang et al. (2018),
Performance CNN Connected AHE ? connected Marium et al. (2017), Rahman and Afrin (2013) and Rao
analysis classification component component
parameters approach analysis ? CNN analysis ? CNN
et al. (2009). Wang et al. (2018) used particle filtering
(%) classification classification method for hand gesture recognition and achieved 92.1%
approach approach of sensitivity, 84.7% of specificity and 90.6% of accuracy.
Marium et al. (2017) used convexity algorithm for hand
Sensitivity 91.5 96.8 98.1
gesture recognition and achieved 90.7% of sensitivity,
Specificity 82.7 89.2 93.4
82.1% of specificity and 87.5% of accuracy. Rahman and
Accuracy 91.6 94.8 96.2
Afrin (2013) used support vector machine for hand gesture
Recognition 90.7 96.2 98.7
rate
recognition and achieved 89.6% of sensitivity, 79.9% of
specificity and 85.7% of accuracy. Rao et al. (2009) used
hidden Markov model for hand gesture recognition and
achieved 90.1% of sensitivity, 82.6% of specificity and
analysis ? CNN classification approach) obtained 98.1% 90.6% of accuracy.
of sensitivity, 93.4% of specificity and 96.2% of accuracy The analysis work is performed using recognition time
with 98.7% of recognition rate. From Table 3, it is very which can be computed by the total execution time for
clear that the proposed hand gesture detection methodology recognizing the single hand gesture image for an automated
using CNN classification approach combined with CC process. It is essential for real-time applications for pro-
algorithms provides optimum results when compared with cessing the hand gestures under different environmental
CNN classification approach alone. conditions. Table 6 shows the performance comparisons of
The proposed methodology is also analyzed using SVM proposed methodology with state of art in terms of
classification approach. The methodology with recognition time (s).
AHE ? connected component analysis? SVM classifica- The proposed CNN classification approach based on CC
tion approach achieved 92.1% of sensitivity, 89.9% of algorithm with enhancement technique stated in this paper

123
An efficient method for human hand gesture detection and recognition using deep learning… 15247

Table 5 Performance comparisons of proposed methodology with state of art

Authors and year Methodology Sensitivity Specificity Accuracy
(%) (%) (%)

Proposed methodology (in this CNN classification approach based on CC algorithm with 98.1 93.4 96.2
paper) enhancement technique
Sharma et al. (2019) Static hand gesture algorithm 93.2 91.1 91.8
Wang et al. (2019) Super-pixel 94.2 90.8 92.6
Earth mover’s distance classification algorithm
Wang et al. (2018) Particle filtering method 92.1 84.7 90.6
Chaikhumpha and Hidden Markov models 90.5 91.7 91.6
Chomphuwiset (2018)
Marium et al. (2017) Convexity algorithm 90.7 82.1 87.5
Rahman and Afrin (2013) Support vector machine 89.6 79.9 85.7
Rao et al. (2009) Hidden Markov model 90.1 82.6 90.6

Table 6 Performance comparisons of proposed methodology with state of art in terms of recognition time (s)
Authors and year Methodology Recognition time
(s)

Proposed methodology (in this paper) CNN classification approach based on CC algorithm with enhancement 0.356
technique
Proposed methodology (in this paper) SVM classification approach based on CC algorithm with enhancement 0.674
technique
Sharma et al. (2019) Static hand gesture algorithm 0.810
Wang et al. (2019) Super-pixel 0.768
Earth mover’s distance classification algorithm
Wang et al. (2018) Particle filtering method 0.789
Chaikhumpha and Chomphuwiset Hidden Markov models 0.973
(2018)
Marium et al. (2017) Convexity algorithm 1.372
Rahman and Afrin (2013) Support vector machine 2.102
Rao et al. (2009) Hidden Markov model 1.357

consumed 0.356 s as recognition time, whereas the con- classification approach trains and classifies the test hand
ventional methods in Wang et al. (2018) consumed 0.789 s, gesture image which is obtained from open access image
Chaikhumpha and Chomphuwiset (2018) consumed dataset. The performance of the proposed hand gesture
0.973 s, Marium et al. (2017) consumed 1.372 s, Rahman detection and recognition methodology is analyzed in
and Afrin (2013) consumed 2.102 s and Rao et al. (2009) terms of sensitivity, specificity, accuracy and recognition
consumed 1.357 s. From Table 4, it is very clear that the rate. The proposed hand gesture detection and recognition
proposed methodology for gesture recognition consumed methodology using CNN classification approach stated in
less recognition rate when compared with conventional this paper achieves 98.1% of sensitivity, 93.4% of speci-
methodologies. ficity, 96.2% of accuracy and 96.2% of recognition rate.

5 Conclusions
Compliance with ethical standards
In this paper, deep learning convolutional neural network- Conflict of interest All authors state that there is no conflict of
based hand gesture detection and recognition methodology interest.
is proposed. This proposed method segments the finger tips
from the hand gesture image, and then, this finger tips are Human and animal rights Humans/animals are not involved in this
work.
given as input to the CNN classifier. The CNN

123
15248 P. S. Neethu et al.

References Rao J, Gao T, Gong Z, Jiang Z (2009) Low cost hand gesture learning
and recognition system based on hidden markov model. In:
Proceedings of the 2009 2nd international symposium on
Ashfaq T, Khurshid K (2016) Classification of hand gestures using
information science and engineering (ISISE ‘09), IEEE, Shang-
gabor filter with bayesian and naı̈ve bayes classifier. Int J Adv
hai, China, December 2009, pp 433–438
Comput Sci Appl 7(3):276–279
Rautaray SS, Agrawal A (2015) Vision based hand gesture recogni-
Chaikhumpha T, Chomphuwiset P (2018) Real—time two hand
tion for human computer interaction: a survey. Artif Intell Rev
gesture recognition with condensation and hidden Markov
43(1):1–54
models. In: 2018 international workshop on advanced image
Ren Z, Yuan J, Meng J, Zhang Z (2013) Robust part-based hand
technology (IWAIT), Chiang Mai, 2018, pp 1–4
gesture recognition using kinect sensor. IEEE Trans Multimed
Elmezain M, Al-Hamadi A, Michaelis B (2010) A robust method for
15(5):1110–1120
hand gesture segmentation and recognition using forward
Sharma S, Jain S, Khushboo (2019) A static hand gesture and face
spotting scheme in conditional random fields. In: Proceedings
recognition system for blind people. In: 2019 6th international
of the 20th international conference on pattern recognition
conference on signal processing and integrated networks (SPIN),
(ICPR’10), August 2010, pp 3850–3853
Noida, India, 2019, pp 534–539
Hong J, Kim ES, Lee H-J (2012) Rotation-invariant hand posture
Suguna R, Neethu PS (2017) Hand gesture recognition using shape
classification with a convexity defect histogram. In: IEEE
features. Int J Pure Appl Math 117(8):51–54
international symposium on circuits and systems (ISCAS)
Tauseef H, Fahiem MA, Farhan S (2009) Recognition and translation
20–23 May 2012, pp 774–777
of hand gestures to Urdu alphabets using a geometrical
Kapil Y, Bhattacharya J (2016) Real-time hand gesture detection and
classification. In: Proceedings of IEEE international conference
recognition for human computer interaction. In: Berretti S,
on visualisation (VIZ), Barcelona, Spain, pp 213–217
Thampi S, Srivastava P (eds) Intelligent systems technologies
Wang Z, Chen B, Wu J (2018) Effective inertial hand gesture
and applications. Springer, Cham, pp 559–567
recognition using particle filtering based trajectory matching.
Kawulok M, Grzejszczak T, Nelapa J, Knyc M (2012) Database for
J Electric Comput Eng 2018, 6296013
hand gesture recognition. http://sun.aei.polsl.pl/*mkawulok/
Wang Y, Jung C, Yun I, Kim J (2019) SPFEMD: super-pixel based
gestures/. Accessed 12 May 2018
finger earth mover’s distance for hand gesture recognition. In:
Liu K, Chen C, Jafari R, Kehtarnavaz N (2014) Fusion of inertial and
ICASSP 2019–2019 IEEE international conference on acoustics,
depth sensor data for robust hand gesture recognition. Sens J
speech and signal processing (ICASSP), Brighton, United
IEEE 14(6):1898–1903
Kingdom, 2019, pp 4085–4089
Manresa-Yee C, Varona J, Mas R, Perales FJ (2005) Hand tracking
Yao Y, Fu Y (2014) Contour model-based hand-gesture recognition
and gesture recognition for human–computer interaction. Elec-
using the Kinect sensor. IEEE Trans Circ Syst Video Technol
tronic letters on computer vision and image analysis 5(3):96–104
24(11):1935–1944
Marium A, Rao D, Crasta DR, Acharya K, D’Souza R (2017) Hand
Yasukochi N, Mitome A, Ishii R (2008) A recognition method of
gesture recognition using webcam. Am J Intell Syst 7(3):90–94
restricted hand shapes in still image and moving image as a
Mitra S, Acharya T (2007) Gesture recognition: a survey. IEEE Trans
man–machine interface. In: IEEE conference on human system
Syst Man Cybern Part C Appl Rev 37(3):311–324
interactions, pp 306–310
Park S, Yu S, Kim J, Kim S, Lee S (2012) 3D hand tracking using
Yrk E, Konukoglu E, Sankur B, Darbon J (2006) Shape-based hand
Kalman filter in depth space. EURASIP J Adv Signal Process
recognition. IEEE Trans Image Process 15(7):1803–1815
2012(1), 36
Rahman MH, Afrin J (2013) Article: hand gesture recognition using
multiclass support vector machine. Int J Comput Appl Publisher’s Note Springer Nature remains neutral with regard to
74(1):39–43 jurisdictional claims in published maps and institutional affiliations.

123