Download Cartoonifying Images using Image Processing Techniques and more Study Guides, Projects, Research Digital Image Processing in PDF only on Docsity!
A
Project Report
on
Cartoonify Image
Submitted in partial fulfillment of the requirements
for the award of the degree of
Bachelor of Technology
in
Computer Science and Engineering
by
Ekagra Gupta (19009701000 44 )
Manvi Solanki (1 900970100061 )
Shivangi Chaudhary(1 900970100110 )
Under the Supervision of
Ms. Ritu Dewan
Galgotias College of Engineering & Technology
Greater Noida, Uttar Pradesh
India- 201306
Affiliated to
Dr. A.P.J. Abdul Kalam Technical University
Lucknow, Uttar Pradesh,
India- 226031
December, 2022
GALGOTIAS COLLEGE OF ENGINEERING & TECHNOLOGY
GREATER NOIDA, UTTAR PRADESH, INDIA- 2 01306.
CERTIFICATE
This is to certify that the project report entitled “ CARTOONIFY IMAGE ” submitted by Mr. Ekagra Gupta (1900970100044) , Ms. Manvi Solanki (1900970100061) , Ms. Shivangi Chaudhary (1900970100110) to the Galgotias College of Engineering & Technology, Greater Noida, Uttar Pradesh, affiliated to Dr. A.P.J. Abdul Kalam Technical University Lucknow, Uttar Pradesh in partial fulfillment for the award of Degree of Bachelor of Technology in Computer Science & Engineering is a bonafide record of the project work carried out by them under my supervision during the year 2021 - 2022. Ms. Ritu Dewan Assistant Professor Dept. of CSE Dr. Vishnu Sharma Professor and Head Dept. of CSE
ABSTRACT
Image Processing – In the field of the research processing of an image consisting of identifying an object in an image, identify the dimensions, no of objects, changing the images to blur effect and such effects are highly appreciated in this modern era of media and communication. There are multiple properties in the Image Processing. Each of the property estimates the image to be produced more with essence and sharper image. Each Image is examined to various grid. Each picture element together is viewed as a 2-D Matrix. With each of the cell store different pixel values corresponding to each of the picture elements. Image process could be a methodology to perform some operations on a picture, it's a kind of signal process within which input is a picture and the output might be an image or characteristics/features related to that image. Image process tools include OpenCV, Scikit Image, and Numpy. In our project, we will be taking an image as an input and applying multiple image processing and machine learning techniques to convert it into a cartoonified version. OpenCV is an Associate in Nursing ASCII text file python library used for pc vision and machine learning. it's principally geared toward time period pc vision and image process. Numpy could be a library for scientific computing in Python. It provides a superior flat array object and tools for operating with these arrays. KEYWORDS: dimensions, cartooning, image pixels, image processing, and sharp image
CONTENTS Title Page CERTIFICATE i ACKNOWLEDGEMENT ii ABSTRACT iii CONTENTS iv LIST OF FIGURES v CHAPTER 1: INTRODUCTION 1.1 Identifying the edges 2 1.2 Colours to the RGB image 3 CHAPTER 2: LITERATURE REVIEW 2.1 A Basic study of image processing and its application areas 4 2.2 Cartooning an Image Using OpenCV and Python 4
- 3 Global thresholding algorithm based on boundary selection 5
- 4 Adaptive Thresholding: A comparative study 5 2.5 Parallel K-Means Clustering for Image Colour Quantization 6 CHAPTER 3: PROBLEM FORMULATION 7 CHAPTER 4: PROPOSED WORK 8 CHAPTER 5: SYSTEM DESIGN 19 CHAPTER 6: IMPLEMENTATION 22 CHAPTER 7: RESULT ANALYSIS 25 CHAPTER 8: CONCLUSION AND FUTURE SCOPE 26 REFERENCE 27
CHAPTER 1 : INTRODUCTION
A cartoon is a popular art form that has been widely applied in diverse scenes. Cartooning of image is a motion picture that relies on a sequence of illustrations for its animation. Modern cartoon animation workflows allow artists to use a variety of sources to create content. Some famous products have been created by turning real-world photography into usable cartoon scene materials, where the process is called image cartoonization. Actual image Cartoonified image Fig. 1.1 The conversion of actual image to cartoon image
The process to create a cartoon effect image can be initially branched into 2 divisions
- To detect, blur and bold the edges of the actual RGB color image.
- 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. Fig. 1.2 Cartoon image obtained through various steps 1.1 IDENTIFYING THE EDGES: Finding a smooth outline that represents or bounds the shape of the image is an important property to achieve a quality image. All Edge processing tasks are: 1.1.1. Median Filter – This filter helps in reducing the noise created during the downscaling the image and later converting the original image to cartoon image by applying the bilateral filter. Any extreme specks are smoothened over. 1.1.2. Edge Detection – At first the noise of the image is removed within the
CHAPTER 2 : LITERATURE REVIEW
2 .1. A BASIC STUDY OF IMAGE PROCESSING AND ITS APPLICATION
AREAS
We have presented the basics of image processing, image acquisition, image enhancement, Image restoration, and image compression and its applications such as artistic effects Bio- Medical, and Industrial inspection. There are many more complex modifications we can make to the images. The filters use mathematical algorithms to modify the image. Some filters are easy to use, while others require a great deal of technical knowledge. Image processing help students of computer science, Electronics, IT, Bio-Medical, Mechanical, electrical, etc. Image Acquisition means sensing an image. Image Enhancement means improvement in the appearance of the image. Image Restoration to restore an image. Image Compression to reduce the amount of data of an image to reduce the size. Author - Shonima Vasudevan and Dr. M. Nagarajan Published - Vol. 6 Issue 07, July – 2017 (International Journal of Engineering Research & Technology (IJERT) 2 .2. CARTOONING AN IMAGE USING OpenCV AND PYTHON In the field of research processing, an image consists of identifying an object in an image, identifying the dimensions, and no of objects, and changing the images to blur effect, and such effects are highly appreciated in this modern era of media and communication. There are multiple properties in Image Processing. Each of the properties estimates the image to be produced more with essence and sharper image. Each Image is examined on various grids. Each picture element together is viewed as a 2-D Matrix. Firstly, we use a high-resolution camera to take picture of the internal structure of the wire. Secondly, we use OpenCV image processing functions to implement image pre-processing. Thirdly we use morphological opening and closing
operations to segment images because of their blur image edges. Author-Vaishali Sudarshan, Amritesh Singh Published - 02 | 2020 (International Journal of Interdisciplinary Innovative Research & Development ( IJIIRD )) 2.3. GLOBAL THRESHOLDING ALGORITHM BASED ON BOUNDARY SELECTION A global image thresholding algorithm based on boundary selection is proposed for improving conventional histogram-based thresholding algorithms. An image is divided into blocks of a fixed size, and the pixel variance of each block is used for finding the boundary blocks that a bimodal histogram. Otsu’s threshold value of boundary block is used to classify object blocks and background blocks. The average values of these blocks are used to determine the optimal threshold value. Experimental results show that proposed algorithm improves on conventional thresholding methods for various types of images. Author - Jin-Won Jang, Sewon Lee, Hee-Jung Hwang, Kwang-Ryul Baek Published - Oct. 20 - 23, 2013 (13th International Conference on Control, Automation and Systems (ICCAS 2013)) 2.4. ADAPTIVE THRESHOLDING: A COMPARATIVE STUDY With the growth of image processing applications, image segmentation has become an important part of image processing. The simplest method to segment an image is thresholding. Using the thresholding method, the segmentation of an image is done by fixing all pixels whose intensity values are more than the threshold to a foreground value. The remaining pixels are set to a background value. Such a technique can be used to obtain binary images from grayscale images. The conventional thresholding techniques use a global threshold for all pixels, whereas adaptive thresholding changes the threshold value dynamically over the image. This paper offers a comparative study on adaptive thresholding techniques to choose the accurate method for binarizing an image based on the contrast, texture, resolution etc. of an image
CHAPTER 3 : PROBLEM FORMULATION
3.1 DESCRIPTION OF PROBLEM DOMAIN
Creating a cartoon-like effect is time and space-consuming. Existing solutions to provide cartoon-like effects to images are complex. Some solutions involve installing complex photo editing software like photoshop and others involve performing some tasks by the user. Our project provides you to carry out the task of applying effects that is more suitable, space efficient, and take minimum user effort. for example, cartoony photos is an existing website to perform such tasks but it is difficult to use as the user has to mark down points & lines on the image to apply effects which are not user-friendly also the options are limited. Hence, there is a dire need for user-friendly software that effectively applies effects to images very well. 3.2 PROBLEM STATEMENT To set the value of K(the number of color clusters to be formed ) according to the user.The important feature is to reduce the color palette in order to achieve the cartoon image which is done using the K. Here the user will have the liberty to select his desired number of
3. 3 OBJECTIVES This project plans to create an application with a simple user interface allowing users to apply cartoon filters to images of their choice.The filters are designed to provide artistically and comically appealing results on a wide range of pictures. The system needs to focus on the program's simplicity as the code is written in Python language, which is considered the most' fun' and easy to understand yet with a wide range of applications in every field.The interface is not bound to be used by any age group and any system or service providers. It can be easily accessed from any device
CHAPTER 4 : PROPOSED WORK
4.1 INTRODUCTION
In this project, we examined the real-life image-to-cartoon Image synthesis problem by using a Selective Gaussian Filter (SGF) and Mean Shift Cluster operation. In this paper, the color unification method is proposed in detail. In this method, the color unification model has been developed based on the mean shift. Input images are given into the model and the Gaussian filter blurs the input image by using the Gaussian function, which is also known as Gaussian smoothing. Where the adaptive threshold-based edges automatically find the threshold value of the image and also select the edges which are stronger than the threshold. In mean shift clustering groups, the data points have a high density in a region and add up all the individual kernels to generate a probability surface depending on the kernel bandwidth parameter and perform masking. After masking, we obtain the cartoon image. Fig. 4.1 Step wise explanation of each process
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 color image and mask it with edges. This creates a beautiful cartoon image with edges and lightened color of the original image. Step 4- Transforming an image to grayscale cvtColor(image, flag) is a method in cv2 which is used to transform an image into the colour-space mentioned as ‘flag’. Here, our first step is to convert the image into grayscale. Thus, we use the BGR2GRAY flag. This returns the image in grayscale. A grayscale image is stored as grayScaleImage. After each transformation, we resize the resultant image using the resize() method in cv and display it using imshow() method. This is done to get more clear insights into every single transformation step Fig. 4.2 Transformation of image into greyscale Step 5 - Smoothening a grayscale image
To smoothen an image, we simply apply a blur effect. This is done using medianBlur() function. Here, the center pixel is assigned a mean value of all the pixels which fall under the kernel. In turn, creating a blur effect. Fig. 4.3 Smoothening of greyscale image using blur effect Step 6- Retrieving the edges of an image Cartoon effect has two specialties:
- Highlighted Edges
- Smooth colors In this step, we will work on the first specialty. Here, we will try to retrieve the edges and highlight them. This is attained by the adaptive thresholding technique. The threshold value is the mean of the neighborhood pixel values area minus the constant C. C is a constant that is subtracted from the mean or weighted sum of the neighborhood pixels. Thresh_binary is the type of threshold applied, and the remaining parameters determine
Fig. 4.5 Images are lightened in colour Step 8 - Giving a Cartoon Effect combine the two specialties. This will be done using MASKING. We perform bitwise and on two images to mask them.
Fig. 4.6. Cartoonified image is obtained This finally CARTOONIFY our image! Step 9- Plotting all the transitions together To plot all the images, we first make a list of all the images. The list here is named “images” and contains all the resized images. Now, we create axes like subl=plots in a plot and display one-one images in each block on the axis using imshow() method. plt.show() plots the whole plot at once after we plot on each subplot. Step 10- Functionally of save or download button he idea is to save the resultant image. For this, we take the old path, and just change the tail (name of the old file) to a new name and store the cartoonified image with a new name in the same folder by appending the new name to the head part of the file. For this, we extract the head part of the file path by os.path.dirname() method. Similarly, os.path.splitext(ImagePath)[1] is used to extract the extension of the file from the path. Here, newName stores “Cartoonified_Image” as the name of a new file. os.path.join(path1, newName + extension) joins the head of path to the newname and extension. This forms the complete path for the new file.imwrite() method of cv2 is used to save the file at the path mentioned. cv2.cvtColor(ReSized6, cv2.COLOR_RGB2BGR) is used to assure that no color get extracted or highlighted while we save our image. Thus, at last, the user is given confirmation that the image is saved with the name and path of the file.
