See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/367475637

A SYSTEM FOR CARTOONIFYING AN IMAGE USING PYTHON

Article · January 2023

CITATIONS READS
14 2,520

5 authors, including:

Vaibhav Kant Singh Pankaj Chandra

Guru Ghasidas University Guru Ghasidas Vishwavidyalaya, Bilaspur, India
61 PUBLICATIONS 366 CITATIONS 26 PUBLICATIONS 30 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Pankaj Chandra on 03 July 2023.

The user has requested enhancement of the downloaded file.

 A SYSTEM FOR CARTOONIFYING AN IMAGE USING PYTHON

Vaibhav Kant Singh1, Santosh Kumar Soni2 , Dr. Nageshwar Dev Yadav3, Pankaj Chandra4
Assistant Professor, Department of Computer Science & Engineering, School of Studies of
Engineering and Technology, Guru Ghasidas Vishwavidyalaya, Central University, Bilaspur,
Chhattisgarh, India1, Assistant Professor, Department of Information Technology, School of Studies
of Engineering and Technology, Guru Ghasidas Vishwavidyalaya, Central University, Bilaspur,
Chhattisgarh, India2, R & D Product Specialist at Informatica Bangalore3, Assistant Professor,
Department of Information Technology, School of Studies of Engineering and Technology, Guru
Ghasidas Vishwavidyalaya, Central University, Bilaspur, Chhattisgarh, India 4
[email protected], [email protected], [email protected],
[email protected]
ORCID ID: 0000-0002-6776-9573

ABSTRACT
Cartoonization is itself a classic art but, the advancement in the field of Machine Learning is covering
almost every domain. Cartoon-style pictures can be seen almost everywhere in our daily life.
Technology is the mode by which users can store, fetch, communicate and utilize information. Image
processing plays a significant role in all computer-related applications, mainly while processing and
experimenting on images using image processing libraries.
With the recent success of Instagram, the popularity of simple and fun photo effects apps has been on
the rise. The mobile platform presents a unique arena for these applications by connecting users with
both the means to capture images and the computational power to perform sophisticated processing
on these images. Cartooning images seeks to leverage the existing OpenCV library
This work presents an approach to cartoonize digital images into cartoon-like. The method used is
different from what others used previously. This work focuses mainly on various techniques involved
during the whole process, which, when used layer by layer, gives an appropriately balanced output.
We also discuss the algorithms used in the process to make the image cartoonized.
KEYWORD:- ML, CARTOONIZED, PYTHON, OpenCV
INTRODUCTION
Cartoons are illustrations of characters that can be imaginary or based on a personality. They are
semi-realistic or non-realistic, popular nowadays to depict a situation or a happening in a funny,
satirical manner. Animes are so popular that are cartoonized characters. Automation technology is
booming nowadays. Human effort reduced to the minimum; with a set of programs doing our job,
animation technology has taken a considerable leap. Our job is to make those programs. So, this is a
project which converts regular camera clicked images into cartoonized form, created using Python
language and relative libraries. In times like today, where technology is taking huge leaps with
creative minds improving them day by day. Anime movies take much longer than regular movies in
times of VFX effects and animations. The workforce, skillset, and resources in terms of equipment
Volume No. 14, Issue- 5 , October - December 2022 84
and investment are more than classic movies, so time plays an essential role in creating these movies.
For saving time, automation is the best way to go; with improvement in machine learning and artificial
intelligence, every production process has improved significantly and improved the quality of the
product.Playing with images is a fun activity, and recently, image processing has outburst social sites,
with many people making careers in image processing and enhancement. The OpenCV library works
on the same thing, and here we get to know the backend procedures of image processing and
understand how computer vision works. These filters and techniques improve lost details on older
photos, and with a combination of some filters, one of them is converting an black and white image
to a colored one.There are numerous ways to convert a specific photo to a cartoonized one, but the
best way is to do a manual with software like Adobe Photoshop, and not everyone has their hands on
tools like these, so the users there are limited. Although the output we obtain from the manual process
is the best, it is time-consuming, and doing it for many images is not efficient. Therefore, systems
like these are a go-go for every field as it provides output in seconds with upgrades, the scale will
surely improve with even better results.We can do it with a limited number of lines of code in a
programming language with better results using OpenCV library and machine learning algorithms in
python.To achieve the basic cartoon effect, we don't need powerful rendering software or even years
of experience. All we need is essentially a bilateral filter and some edge detection. The bilateral filter
will reduce the color palette, which is essential for the cartoon look, and edge detection will allow
you to produce bold silhouettes.
PROBLEM STATEMENT
In the current time social media has encompassed around the whole globe. In the globe it is being
used by almost all age groups. You can think of the amount the social media is utilized. It is used for
several purposes. There is an issue that is to be addressed in the utilization of the social media i.e.,
Security. The authors of the report tried to find out a Way in which we can incorporate security.In
recent times usage of applications that includes converting images into different forms and styles is
getting craze all over the globe. Here comes the issue. We can’t trust some sites as they might steal
our information like mainly images and may use them in a bad way that affect them. We can simply
do this with some lines of codes using OpenCV. The authors made an implementation in python
language that is very user friendly to address the problem. The security issue is a serious issue as it
may cause catastrophic results. So, looking to the need the authors went to the development which is
presented in this report

LITERATURE SURVEY
AUTHORS AND
S.NO TITLE OF PAPER PUBLICATIONS SUMMARY
DETAILS

Volume No. 14, Issue- 5 , October - December 2022 85

 Intel's OpenCV is a free and
open-access image and video
processing library. It is linked to
computer vision, like feature and
object recognition and machine
learning. This paper presents the
main OpenCV modules,
features, and OpenCV based on
Python. The paper also presents
common OpenCV applications
and classifiers used in these
Face Detection and Hasan, Ramadan & applications like image
1
Recognition Using OpenCV Sallow, Amira. processing, face detection, face
recognition, and object
detection. Finally, we discuss
some literary reviews of
OpenCV applications in the
fields of computer vision such as
face detection and recognition,
or recognition of facial
expressions such as sadness,
anger, happiness, or recognition
of the gender and age of a
person.
Clustering kmeans is an
unsupervised method of
classification, it is robust fast
and very easy to be
implemented, but it suffers
from: the initialization and local
solution. Evolutionary
algorithms are particular
methods for optimizing
Evolutionary Clustering functions; they have a great
2 El allaoui, Ahmad
Kmeans ability to find the global
optimum of a problem. In this
work, we propose a clustering
method based on Kmeans
algorithm, and evolution
strategies noted evolutionary
Kmeans EKM. The proposed
approach is validated by the
artificial dataset and well-knonw
real data sets. We compared our

Volume No. 14, Issue- 5 , October - December 2022 86

 approach with Kmeans, Fuzzy
CMeans and Kmediod. The
results show the good
performance of this approach

Ruttkay, Human faces are attractive and

Zsófia&Noot, Han. effective in every-day
communication. In human-
computer interaction, because of
the lack of sufficient knowledge
and appropriate tools to model
and animate realistic 3D faces,
2D cartoon faces are feasible
alternatives with the extra appeal
of 'beyond realism' features. We
International
discuss Cartoon, an interactive
3 Animated Cartoon faces Symposium on Non-
system to design and animate 2D
Photorealistic
cartoon faces. We give
Animation and
illustrations (also movies on
Rendering
CD) of the expressive and
artistic effects which can be
produced. Cartoon is fully
implemented in Java, allows
real-time animation on PCs and
through the Web. It has been
used with success by different
types of users.
In the Python world, NumPy
arrays are the standard
representation for numerical
data and enable efficient
implementation of numerical
The NumPy Array: A Structure van der Walt, computations in a high-level
4 for Efficient Numerical Stéfan& Colbert, S. language. As this effort shows,
Computation. &Varoquaux, Gael. NumPy performance can be
improved through three
techniques: vectorizing
calculations, avoiding copying
data in memory, and minimizing
operation counts.
5 Informed Machine Learning –
Volume No. 14, Issue- 5 , October - December 2022 87
 A Taxonomy and Survey of In this paper, we presented a
Integrating unified classification framework
for the explicit integration of
additional prior knowledge into
machine learning, which we
described using the umbrella
term of informed machine
learning. Our main contribution
is the development of a
taxonomy that allows a
structured categorization of
approaches and the uncovering
Laura von Rueden et
of main paths. Moreover, we
Prior Knowledge into Learning al
presented a conceptual
Systems
clarification of informed
machine learning, as well as a
systematic and comprehensive
research survey. This helps
current and future users of
informed machine learning to
identify the right methods to use
their prior knowledge, for
example, to deal with
insufficient training data or to
make their models more robust.
In this paper, we proposed to
Deep Multiple Instance Jiajun Wu1, Yinan construct a deep learning
Learning Yu, Chang Huang framework within a weakly
supervised learning setting.
We demonstrated that our
observation of the universal
existence of the multiple
instance assumption contributes
much in solving computer vision
6 tasks, and the deep multiple
, Kai Yu
instance learning system we
for Image Classification and Massachusetts
developed performs well in both
Auto-Annotation Institute of
image classification and image
Technology
auto-annotation. Our system is
also able to automatically extract
correspondences between object
and keyword proposals and
return meaningful region-
keyword pairs on widely used

Volume No. 14, Issue- 5 , October - December 2022 88

 benchmarks. We hope our
findings could arouse further
research in the fields of deep
learning and weakly supervised
learning in the vision
community.346

Institute of Deep
Learning, Baidu
Tsinghua University
Deep Challenges Associated In this paper, various work has
with Deep been discussed related to hidden
layers, network structure,
activation functions, loss
functions, model optimization,
epochs and batch size. These
areas bring challenge to deep
7 Ochin Sharma
learning field not only in
Learning
theoretical designing but while
implementing the model
experimentally. So, researchers
may find these to work with and
provide efficient solutions for
these.
In this paper, we talk about
structure of CNN and all the
models of CNN which are
proposed till date.
Convolutional Neural Network
has proved to be an important
tool in Machine Learning field.
Diving deep in Deep Divya Arora Mehak Although there still lies open
8
Convolutional Neural Network Garg Megha Gupta issues like reducing the
parameters of Fully Connected
layer and reducing the error rate
when the network is exposed to
dense data. It has proved that
adding more layers improve the
performance but also increase
the parameters with each layer.

Volume No. 14, Issue- 5 , October - December 2022 89

 In order to solve the problems of
low recognition rate and
complex algorithm of traditional
facial expression recognition
methods, an improved facial
expression recognition
algorithm based on
convolutional neural network
(CNN) was proposed. The
convolutional neural network
uses batch regularization and
ReLU activation function to
solve the problem of gradient
disappearance. The Dropout
technology is introduced to
solve the problem of network
overfitting. Experimental results
show that the improved
convolutional neural network
can improve the accuracy of face
A Facial Expression JianchengZoua,
expression image recognition
Recognition Based on XiulingCaob, Sai
9 Convolution of the
Improved Convolutional Zhangc and Bailin
characteristics of neural network
Neural Network Ged
is compared with the traditional
neural network complexity
greatly reduced, also can omit
artificially feature extraction, the
pretreatment of image input to
the convolutional neural
network can automatically learn
to face facial subtle features, this
paper puts forward the add batch
regularization and ReLU
activation function convolution
neural network compared with
the original convolution neural
network in the rate increased
CK+ data sets, late work will be
blocked from solution to
recognize faces expression and
improve the training speed of the
network problems, further
optimize the network.

Volume No. 14, Issue- 5 , October - December 2022 90

 Ming Xue, Changjun By combining several basic
Zhu Changchun ideas of main strategies, great
Institute of effort is laid on introducing
Technology several machine learning
methods, such as Rote learning,
Explanation-based learning,
learning from instruction,
learning by deduction, Learning
by analogy and Inductive
learning, etc. Meanwhile,
comparison and analysis are
made upon their respective
advantages and limitations. At
the end of the article, it proposes
the research objective of
machine learning and points out
its development trend. Machine
learning is a fundamental way
A Study and Application on
that enable the computer to have
10 Machine Learning of Artificial
the intelligence; Its application
Intellligence
Changchun,130012, which had been used mainly the
China method of induction and the
synthesis，rather than the
deduction has already reached
many fields of Artificial
Intelligence. AI science is the
only way that raises the machine
intelligence level. Only improve
the machine- learning function
continuously, can we make the
machine close to or surpasses
the humanity's intelligent level.
To the ML discussion and the
ML research progress, will
certainly make the artificial
intelligence and the entire
science and technology further
development.
In this study, various machine
learning techniques and its
A Survey on machine learning Dr. Roopam Gupta et approaches were analyzed. The
11
approaches and its Techniques al classification of machine
learning approaches such as
supervised learning,

Volume No. 14, Issue- 5 , October - December 2022 91

 unsupervised learning, semi-
supervised learning and
reinforcement learning and its
various algorithms are the
important contributions of this
study. In future we intend to
develop a model based on
machine learning techniques.
An Approach for Non- This paper presents a framework
Photorealistic Rendering designed to generate
cartoon-like abstracted images,
which combines techniques for
region smoothing and
segmentation, edge detection,
adjustment of
brightness/saturation and color
harmonization. A subjective
evaluation involving the output
of related work was
performed.Additionally, an
J. B. de O. Alencar
experimental study involving
Junior, J. E. R. de
12 human evaluators was
that is Appealing to Human Queiroz, H. M.
conducted, in which the
Viewers Gomes
proposed approach was
compared with five existing
tools for image cartoonization.
Statistical analysis performed on
experimental data from one-way
(1-F) ANOVA and Tukey-
Kramer tests revealed
significant differences in
preference between results
created by the proposed
approach and those created by
the competing approaches
An Exploration on Text Text classification is an essential
Classification with Classical part of the NLP, which
aims to predict the categories for
given texts in a particular
13 Yuhan Zheng classification system. There are
Machine Learning Algorithm many ways of feature selection
and classification models.
However, most researchers
would like to use the
Volume No. 14, Issue- 5 , October - December 2022 92
 encapsulated methods of third-
party libraries to achieve their
goals. Therefore, in this paper,
we propose to implement code
to achieve functions, instead of
using third-party libraries. We
evaluate our code in different
classification models, and the
result of our experiment shows
that our code is feasible.
Proposing Solution to XOR
Author Proposed an ANN
14 problem using minimum V.K. Singh
Model
configuration MLP
Minimum Configuration MLP V.K. Singh and S. Authors Proposed a Novel
15
for Solving XOR problem Pandey Model for ANN
Proposing an Ex-NOR Solution V.K. Singh and S. Authors Proposed an Ex-NOR
16
using ANN Pandey Model
Mathematical Explanation to
Mathematics behind ANN in
17 Solution for Ex-NOR Problem V.K. Singh
LSP is conveyed by Author
Using MLFFN
Mathematical Analysis for
General Mathematics in ANN is
18 Training ANNs Using Basic V.K. Singh
portrayed
Learning Algorithms
Mathematical Analysis for
General Mathematics in ANN is
19 Training ANNs Using Basic V.K. Singh
portrayed
Learning Algorithms
Minimizing Space Time
Complexity in Frequent Pattern
V.K. Singh and V Data Mining is discussed by the
20 Mining by Reducing Database
Shah Authors
Scanning and Using Pattern
Growth Method
The Huge Potential of Information V.K. Singh and V.K. Information Technology
21
Technology Singh Landscape is discussed
Proposing pattern growth
methods for frequent pattern
mining on account of its Frequent Pattern Mining is
22 V.K. Singh
comparison made with the discussed by the Author
candidate generation and test
approach for a given data set
RSTDB & Cache Conscious
RSTDB Algorithm is discussed
23 Techniques for Frequent Pattern V.K. Singh
by the Author
Mining

Volume No. 14, Issue- 5 , October - December 2022 93

 Designing simulators for various
VLSI designs using the proposed TRIVENI Model is discussed by
24 V.K. Singh
artificial neural network model Author
TRIVENI
Analysis of Stability and
Convergence is given a look by
25 Convergence on Perceptron V.K. Singh
the Author
Convergence Algorithm
V.K. Singh, A.
Breast Cancer and Machine
Machine Learning approach to Baghel, N.D. Yadav,
26 Learning Discussed by the
detect Breast Cancer M. Sahu and M.
authors
Jaiswal
SVM using rbf as kernel for RBF Kernel is Discussed by the
27 V.K. Singh
Diagnosis of Breast Cancer author
Support Vector Machine using
rbf, polynomial, linear and
sigmoid as kernel to detect Diabetes is Discussed by the
28 V.K. Singh
Diabetes Cases and to make a Author
Comparative Analysis of the
Models
Colorization of old gray scale
Deep learning is used as Idea in
29 images and videos using deep V.K. Singh
the paper by the authors
learning
Dual Secured Data
Security aspect is discussed in
30 Transmission using Armstrong V.K. Singh
the paper by the author
Number and Color Coding
Finding New Framework for
Resolving Problems in Various
Dimensions by the use of ES: V.K. Singh, A. Expert System is discussed by
31
An Efficient and Effective Baghel and S.K. Negi the Authors
Computer Oriented Artificial
Intelligence Approach
Chandrashekhar, R.
The authors did ML Technology
32 Twitter Sentiment Analysis Chauhan and V.K.
for Twitter Sentiment Analysis
Singh
P. Kumari, R. Gupta,
ML Approach for Detection of ML is utilized in the area of
33 S. Kumar and V.K.
Lung Cancer Lung Cancer
Singh
P. Sailokesh, S. Authors implemented
Automatic Number Plate
34 Jupudi, I.K. Vamsi Automatic Number Plate
Recognition
and V.K. Singh Recognition System
Y.K. Reddy, K.M.
Authors Proposed Human
35 Human Activity Recognition Yadav and V.K.
Activity Recognition
Singh

Volume No. 14, Issue- 5 , October - December 2022 94

 R.N.R.K. Prasad,
P.S.S.R Ram, S. Authors Proposed Text
36 Text Summarization
Dinesh and V.K. Summarization System
Singh
Diagnosis of Breast Cancer V.K. Singh, N.D.
Detection of Breast Cancer is
37 using SVM taking polynomial Yadav and R.K.
discussed
as Kernel Singh

PROPOSED WORK

Load the image • input

image.
the

• we do that
using
Create edge cvtcolor,medi
anblur and
mask adaptive
threshold
functions.
• using certian
algorithms,
we reduce the
Color colors in the
Quantization image to
make it look
like a cartoon
image. • we use
bilateral
filter and
Reduce the operation. It
gives a bit
Fig-1:-The process happens in the color palatte form of a flowchart.
blurred and
sharpness
Methodology: reducing
effect.
The process to create a cartoon effect image can • using bitwise be
operator we
initially branched into 2 Divisions Combine edge combine the
mask with two images to
1. To detect, blur and bold the edges of the colored image . get the actual
cartoonized
RGB color image. effect.
2. To smooth, quantize and the conversion of the RGB image to grayscale. The results involved
in combining the image and help achieve the desired result.
Steps involved are:
1. We load the image that is to be converted.
2. We go through the edge operations to get the effects of a cartoon i.e., to get thicker edges
around the object (person, thing, etc.) in the image.
3. Then, we reduce the color palette using OpenCV optimized algorithms like Kmeans algorithm
in this step.
4. After doing color quantization, we can reduce the noise of the image using bilateral filter. It
would give a bit blurry and sharpness reducing effect to the image.
Volume No. 14, Issue- 5 , October - December 2022 95
5. The last step is we combine the edge mask with the color processed image. We do that using
the bitwise operation.
RESULT
From the samples some of the results we got, are displayed below.

Fig-2 (Rome Colosseum)

Fig-3 (Taj Mahal)

Fig-4 (Humayunus tomb)

Volume No. 14, Issue- 5 , October - December 2022 96

Fig-5 (Meharangarh fort)

Fig-6 (Khajuraho temple)

These are some results from the code we developed.
CONCLUSION
The project showed that the image was successfully converted into a cartoon-style image with help
of a python library called cv2. It includes the origin and history of image processing, different types
of uncertain environments, existing methods for cartoon imaging. Amid the previous three decades,
the topic of image processing has gained vital name and recognition among researchers because of
their frequent look in varied and widespread applications within the field of various branches of
science and engineering.
The systematic working of an image to cartoon conversion process with a neat flowchart in the paper.
Also, we have stated challenges and problems one can face while cartooning the captured image.
FUTURE WORK
As an example, image processing is helpful to issues in signature recognition, digital video
processing, Remote Sensing, and finance. Firstly, we take input, and then we use OpenCV image
processing functions to implement image pre-processing. We use morphological opening and closing
operations to segment images because of the blur image edges. The main attraction of the paper is to

Volume No. 14, Issue- 5 , October - December 2022 97

solve different types of images having one object, two objects, and three objects which can’t be solved
by any of the existing methods but can be solved by our proposed method.
It is capable of producing exactly the effect specified above, and a wide range of input images will
yield satisfactory results. However, the algorithm is not perfect, and it does not respond predictably
across all inputs. Given the variety of input images, it would be unrealistic to expect a one-size-fits-
all approach to produce consistent results. Thus, we have shown how an image can be converted to a
cartoon. We also stated examples of how an image is converted to a cartoon.
REFERENCES
1. Vaishali Sudarshan, Amritesh Singh,”Cartooning an Image,” International Journal of
Interdisciplinary Innovative Research &Development (IJIIRD) ISSN: 2456-236X Vol. 04 Issue 02
|2020
2. https://users.soe.ucsc.edu/~manduchi/Papers/ICCV98.pdf
3. https://towardsdatascience.com/massive-tutorial-on-image-processing-and-preparation-for-
deep-learning-in-python-1-e534ee42f122
4. Y. Chen, Y.-K. Lai, Y.-J. Liu, "CartoonGAN: Generative Adversarial Network for photo
Cartoonization", International Conference on Image Processing, 2018
5. https://docs.opencv.org/3.4/d3/dc0/group__imgproc__shape.html#ga17ed9f5d79ae97bd4c7c
f18403e1689a
6. https://stacks.stanford.edu/file/druid:yt916dh6570/Dade_Toonify.pdf
7. Chinmay Joshi, Devendra Jaiswal &AkshataPatil “Technical Paper Presentation on
Application of Cartoon like Effects to Actual Images” International Journal of Innovative Science
and Research Technology ISSN No: -2456-2165 Volume 4, Issue 3, March – 2019
8. Nikhil Nautiyal, Veeranarayan Sinha &Savleen Kaur.” Image Cartoonization” International
Journal for Modern trends in Science and technology 7,63-71 (2021).
9. https://www.programcreek.com/python/example/89394/cv2.kmeans
10. https://link.springer.com/chapter/10.1007/978-981-15-5679-1_45
11. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.168.1019&rep=rep1&type=pdf#:
~:text=Adaptive%20thresholding%20technique%20is%20used,and%20to%20highlight%20edge%2
0points.&text=understanding%20of%20edge%20detection%20algorithms,an%20object%20and%2
0the%20background.
12. https://towardsdatascience.com/colour-image-quantization-using-k-means-636d93887061
13. https://towardsdatascience.com/k-means-clustering-explain-it-to-me-like-im-10-
e0badf10734a
14. https://docs.opencv.org/4.x/d4/d86/group__imgproc__filter.html#ga94756fad83d9d24d29c9
bf478558c40a
15. https://docs.opencv.org/3.0-
beta/doc/py_tutorials/py_ml/py_kmeans/py_kmeans_understanding/py_kmeans_understanding.htm
l#kmeans-clustering-understanding

Volume No. 14, Issue- 5 , October - December 2022 98

16. Baggio, Daniel L, Mastering OpenCV with Practical Computer Vision Projects Packt
Publishing Ltd, 2012
17. V.K. Singh, “Proposing Solution to XOR problem using minimum configuration MLP,”
Science Direct, International Conference on Computational Modeling and Security (CMS 2016),
Procedia Computer Science, 85, pp.263-270.
18. V.K. Singh and S. Pandey, “Minimum Configuration MLP for Solving XOR problem,”
Proceeding of the 10th INDIACom, IEEE Conference ID:37465, 3rd International Conference on
Computing for Sustainable Global Development, 168-173, BVICAM, New Delhi, India.
19. V.K. Singh and S. Pandey,” Proposing an Ex-NOR Solution using ANN,” Proceeding
International Conference on Information, Communication and Computing Technology, JIMS, New
Delhi.
20. V.K. Singh, “Mathematical Explanation To Solution For Ex-NOR Problem Using MLFFN,”
International Journal of Information Sciences and Techniques,vol. 6,pp. 105-122, 2016.
21. V.K. Singh., “Mathematical Analysis for Training ANNs Using Basic Learning Algorithms,”
Research Journal of Computer and Information Technology Sciences, 4(7),pp. 6-13,2016.
22. V.K. Singh and V.K. Singh, “Vector Space Model: An Information Retrieval System,”
International Journal of Advanced Engineering Research and Studies, vol. 4(2), pp. 141-143.
23. V.K. Singh and V Shah, “Minimizing Space Time Complexity in Frequent Pattern Mining by
Reducing Database Scanning and Using Pattern Growth Method,” Chhattisgarh Journal of Science
& Technology ISSN: 0973-7219.
24. V.K. Singh and V.K. Singh, “The Huge Potential of Information Technology,” Proceedings
of National Convention on Global Leadership: Strategies and Challenges for Indian Business, Feb
pp.10-11.
25. V.K. Singh,” Proposing pattern growth methods for frequent pattern mining on account of its
comparison made with the candidate generation and test approach for a given data set,” Software
Engineering, pp. 203-209, Springer, Singapore, 2019.
26. V.K. Singh, “RSTDB & Cache Conscious Techniques for Frequent Pattern Mining,” 4th
International Conference on Computer Applications in Electrical Engineering Recent Advances,
CERA-09, Indian Institute of Technology, Roorkee,2010.
27. V.K. Singh, “Designing simulators for various VLSI designs using the proposed artificial
neural network model TRIVENI,” IEEE, International Conference on Information, Communication,
Instrumentation and Control (ICICIC), pp.1-6, 2017.
28. V.K. Singh, “Analysis of Stability and Convergence on Perceptron Convergence Algorithm,”
pp.149-161, International Conference by JIMS Delhi.
29. V.K. Singh, A. Baghel, N.D. Yadav, M. Sahu and M. Jaiswal, “Machine Learning approach
to detect Breast Cancer,” Design Engineering (Toronto), Volume 2021, Issue-08, pp. 7054-7060,
ISSN: 0011-9342, 2021.

Volume No. 14, Issue- 5 , October - December 2022 99

View publication stats

30. V.K. Singh, “SVM using rbf as kernel for Diagnosis of Breast Cancer,” International
Conference on Innovative Research in Science, Management and Technology (ICIRSMT 2021),
Department of Computer Science and Application, Atal Bihari Vajpayee University, Bilaspur (C.G.),
India in association with American Institute of Management and Technology (AIMT), USA,
December 27-28 2021.
31. V.K. Singh, “Support Vector Machine using rbf, polynomial, linear and sigmoid as kernel to
detect Diabetes Cases and to make a Comparative Analysis of the Models,” International Conference
on Innovative Research in Science, Management and Technology (ICIRSMT 2021), Department of
Computer Science and Application, Atal Bihari Vajpayee University, Bilaspur (C.G.), India in
association with American Institute of Management and Technology (AIMT), USA, December 27-
28 2021.
32. V.K. Singh, “Colorization of old gray scale images and videos using deep learning,” Published
in The Journal of Oriental Research Madras, ISSN: 0022-3301, 2021.
33. V.K. Singh, “Dual Secured Data Transmission using Armstrong Number and Color Coding,”
Prestige e-Journal of Management and Research, Volume 3, Issue 1, ISSN: 2350-1316, April 2016.
34. V.K. Singh, A. Baghel and S.K. Negi, “Finding New Framework for Resolving Problems in
Various Dimensions by the use of ES: An Efficient and Effective Computer Oriented Artificial
Intelligence Approach,” Volume 4, No. 11, ISSN(Paper): 2222-1727, ISSN(Online): 2222-2871,
2013.
35. Chandrashekhar, R. Chauhan and V.K. Singh,” Twitter Sentiment Analysis,” ISPEC 8TH
INTERNATIONAL CONFERENCE ON AGRICULTURAL, ANIMAL SCIENCE AND RURAL
DEVELOPMENT, BINGOL, TURKEY, DECEMBER 24-25, 2021.
36. P. Kumari, R. Gupta, S. Kumar and V.K. Singh,” ML Approach for Detection of Lung
Cancer,” ISPEC 8TH INTERNATIONAL CONFERENCE ON AGRICULTURAL, ANIMAL
SCIENCE AND RURAL DEVELOPMENT, BINGOL, TURKEY, DECEMBER 24-25, 2021.
37. P. Sailokesh, S. Jupudi, I.K. Vamsi and V.K. Singh,” Automatic Number Plate Recognition,”
ISPEC 8TH INTERNATIONAL CONFERENCE ON AGRICULTURAL, ANIMAL SCIENCE
AND RURAL DEVELOPMENT, BINGOL, TURKEY, DECEMBER 24-25, 2021.
38. Y.K. Reddy, K.M. Yadav and V.K. Singh,” Human Activity Recognition,” ISPEC 8TH
INTERNATIONAL CONFERENCE ON AGRICULTURAL, ANIMAL SCIENCE AND RURAL
DEVELOPMENT, BINGOL, TURKEY, DECEMBER 24-25, 2021.
39. R.N.R.K. Prasad, P.S.S.R Ram, S. Dinesh and V.K. Singh,” Text Summarization,” ISPEC
8TH INTERNATIONAL CONFERENCE ON AGRICULTURAL, ANIMAL SCIENCE AND
RURAL DEVELOPMENT, BINGOL, TURKEY, DECEMBER 24-25, 2021.
40. V.K. Singh, N.D. Yadav and R.K. Singh,” Diagnosis of Breast Cancer using SVM taking
polynomial as Kernel,” Design Engineering (Toronto), Volume 2021, Issue-08, pp. 6589-6599, ISSN:
0011-9342, 2021.

Volume No. 14, Issue- 5 , October - December 2022 100