Volume 8, Issue 3, March – 2023 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165

Cartoonify Image Using Gan

[1]
Guide - Jayendra Kumar (Assistant Professor)
[2]
Gangam Keerthika; [3] Namani Umesh Chandra; [4]Thadakamalla Abhishek
Department of CSE
Anurag Group Of Institutions

Abstract:- Cartoonization of images and videos could be III. PROPOSED SYSTEM

used in various different applications, which can be ease
in publishing a comic book for a comic, anime, T.V. Keeping the existing system in mind, cartoonization of
shows as well as for fun events on social media. This images and videos through Generative Adversarial
project proposes cartoonization of images and videos Networks (GANs). Thus, an idea to convert real world
through Generative Adversarial Networks (GANs). images and videos into cartoonized one. With
Thus, an idea to convert real world images and videos cartoonization, we also propose to make a complete Image-
into cartoonized one. With cartoonization, we also hub for the user with features including upscaling, denoising
proposes to make a complete Image-hub for the user and editing filters to the input images through the Python
with features including upscaling, denoising and editing OpenCV library. The project also includes video to GIF
filters to the input images through the Python OpenCV conversion to use in various social media platforms to
library. The project also includes video to GIF achieve cartoon filters.
conversion to use in various social media platforms to
achieve cartoon filters. Thus, the project is built to be we propose a Generative Adversarial Networks
user friendly and leveraging various other features (GANs) based approach along with features like image
rather than only cartoonization of images and videos. denoising and image upscaling to convert an image, GIF or
video files into their cartoon versions. The image upscaling
I. INTRODUCTION and denoising is achieved using OpenCV. To train the
model, data used are a set of photos and a set of cartoon
Cartoon is an image or series of images that are formed images. The trained model helps in generating the cartoon
using a sequence of illustrations for animations. These images or videos that are not a part of training data.
cartoons may represent realistic or non-realistic features.
However, cartoons have gained a huge attention especially IV. EXPERMENTAL TOOLS
by the children, teenagers and artists. Due to which there
exists many applications where cartoons are used. Some of  DJANGO
these applications include cartoon television shows, comic Django is a high-level Python web framework that
magazines, cartoon-based image filters and animated films. enables rapid development of secure and maintainable
Some of the applications may also contain some real-world websites. Built by experienced developers, Django takes
scenes. For example, an animated film may contain an care of much of the hassle of web development.
image having a city drawn which corresponds to a city that
is present in a real world.  MYSQL
A relational database stores data in separate tables
II. EXISTING SYSTEM rather than putting all the data in one big storeroom. The
database structure is organized into physical files optimized
In the existing systems, entire process requires a lot of for speed. The logical data model, with objects such as data
labour skills and is really time consuming especially while tables, views, rows, and columns, offers a flexible
working on animated comics or films. Also, the existing programming environment.
computer software’s like Corel Draw or Adobe Photoshop
are not free to use and also may not be easy for the  WAMP SERVER
beginners to understand and achieve the required quality. WampServer refers to a solution stack for the
So, there is a requirement of technology that can help Microsoft Windows operating system, created by Romain
transform a real-world based photo or video into an Bourdon and consisting of the Apache web server, OpenSSL
animated image or video respectively. This technology when for SSL support, MySQL database and PHP programming
integrated with other software’s can help the user to convert language.
their real-world photos or videos into cartoon versions as
and when required or can also act as an image filter which is  VISUAL STUDIO CODE
also freely available and easy to use. Visual Studio Code is a lightweight but powerful
source code editor which runs on your desktop and is
available for Windows, macOS and Linux. It comes with
built-in support for JavaScript, TypeScript and Node.js and
has a rich ecosystem of extensions for other languages and
runtimes.

IJISRT23MAR1438 www.ijisrt.com 1868

Volume 8, Issue 3, March – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165

 RATIONAL ROSE
The Rational Rose is a visual modelling tool from
Rational Software which supports object-oriented modelling
and controlled iterative development.

V. OUTPUT

To convert an image to a cartoon, multiple

transformations are done. Firstly, an image is converted to a
Grayscale image. Yes, similar to the old day’s pictures.!
Then, the Grayscale image is smoothened, and we try to
extract the edges in the image. Finally, we form a colour
image and mask it with edges. This creates a beautiful
cartoon image with edges and lightened colour of the
original image.

(Fig 3. Video Cartoonify)

(Fig 1. Login Page)

(Fig 4. Test Case)

VI. CONCLUSION

We purposed a system that helps in cartoonization of

images and videos with the help of Generative Adversarial
Models (GANs). To implement this, real-world image files
are denoised and then passed through the GAN model which
generates the desired cartoonized image. The video is
cartoonized by dividing the video into multiple image
frames and simultaneously extracting audio from the image
file. Hence, the GAN based Cartoonization model helps with
less noise and better quality.

REFERENCES
(Fig 2. Image Cartoonify)
[1]. Y. Chen, Y.-K. Lai, Y.-J. Liu, "Transforming photos to
comics using convolutional neural networks'',
International Conference on Image Processing, 2017.
[2]. Yang Chen, Yu-Kun Lai, Yong-Jin Liu,
“CartoonGAN: Generative Adversarial Networks for
Photo Cartoonization”,2020.

IJISRT23MAR1438 www.ijisrt.com 1869

Volume 8, Issue 3, March – 2023 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165
[3]. I..Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D.
WardeFarley, S. Ozair, A. Courville, and Y. Bengio,
“Generative adversarial nets,” in Advances in neural
information processing systems, 2014, pp. 2672– 2680.
[4]. Akanksha Apte, Ashwathy Unnikrishnan,
NavjeevanBomble, Prof. SachinGavhane,”
Transformation of Realistic Images and Videos into
Cartoon Images”,2020
[5]. Bee Lim, Sanghyun Son, Heewon Kim Seungjun, Nah
Kyoung Mu Lee,”Enhanced Deep Residual Networks
for Single Image Super-Resolution”,
arXiv:1707.02921v1 [cs.CV], 10 Jul 2017
[6]. Chao Dong, Chen Change Loy, Xiaoou Tang,
“Accelerating the Super-Resolution Convolutional
Neural Network”, arXiv:1608.00367v1 [cs.CV], 1 Aug
2016
[7]. Saurabh Kumar; Utkarsh Bhardwaj; T. Poongodi
“Cartoonify an Image using Open CV in Python” 2022
3rd International Conference on Intelligent
Engineering and Management (ICIEM)
[8]. R. Qian, R. T. Tan, W. Yang, J. Su and J Liu,
"Attentive generative adversarial network for raindrop
removal from a single image", Proceedings of the IEEE
conference on computer vision and pattern recognition,
pp. 2482-2491, 2018.
[9]. Y. Liu, Z. Qin, Z. Luo and H Wang, "Auto-painter:
Cartoon image generation from sketch by using
conditional generative adversarial networks", 2017.
[10]. M. E. Nilsback and A Zisserman, "Automated flower
classification over a large number of classes", 2008
Sixth Indian Conference on Computer Vision Graphics
& Image Processing, pp. 722-729, 2008, December.

IJISRT23MAR1438 www.ijisrt.com 1870