Cartoonify Image with Machine Learning

Cartoonify Image with Machine Learning

Project Idea: Transform images into its cartoon. Yes, the objective of this machine learning project is to CARTOONIFY the images.

Cartoonify an Image with OpenCV in Python

Do you miss your childhood? Yes, everyone does.! So today let’s head towards giving our pictures some cartoonic effects. This article is all about building a photo cartoonifyer using Python and OpenCV

What is OpenCV?

Python is the pool of libraries. It has numerous libraries for real-world applications. One such library is OpenCV. OpenCV is a cross-platform library used for Computer Vision. It includes applications like video and image capturing and processing. It is majorly used in image transformation, object detection, face recognition, and many other stunning applications.

What are we going to build?

At the end of this article, we aim to transform images into its cartoon. Yes, we will CARTOONIFY the images. Thus, we will build a python application that will transform an image into its cartoon using OpenCV.

Step 1: Importing the required modules

We will import the following modules:

CV2: Imported to use OpenCV for image processing

easygui: Imported to open a file box. It allows us to select any file from our system.

Numpy: Images are stored and processed as numbers. These are taken as arrays. We use NumPy to deal with arrays.

Imageio: Used to read the file which is chosen by file box using a path.

Matplotlib: This library is used for visualization and plotting. Thus, it is imported to form the plot of images.

OS: For OS interaction. Here, to read the path and save images to that path.

Code:

import cv2 #for image processing

import easygui #to open the filebox

import numpy as np #to store image

import imageio #to read image stored at particular path

import sys

import matplotlib.pyplot as plt

import os

import tkinter as tk

from tkinter import filedialog

from tkinter import *

from PIL import ImageTk, Image

top=tk.Tk()

top.geometry('400x400')

top.title('Cartoonify Your Image !')

top.configure(background='white')

label=Label(top,background='#CDCDCD', font=('calibri',20,'bold'))

def upload():

    ImagePath=easygui.fileopenbox()

    cartoonify(ImagePath)

def cartoonify(ImagePath):

    # read the image

    originalmage = cv2.imread(ImagePath)

    originalmage = cv2.cvtColor(originalmage, cv2.COLOR_BGR2RGB)

    #print(image)  # image is stored in form of numbers

    # confirm that image is chosen

    if originalmage is None:

        print("Can not find any image. Choose appropriate file")

        sys.exit()

    ReSized1 = cv2.resize(originalmage, (960, 540))

    #plt.imshow(ReSized1, cmap='gray')

    #converting an image to grayscale

    grayScaleImage= cv2.cvtColor(originalmage, cv2.COLOR_BGR2GRAY)

    ReSized2 = cv2.resize(grayScaleImage, (960, 540))

    #plt.imshow(ReSized2, cmap='gray')

    #applying median blur to smoothen an image

    smoothGrayScale = cv2.medianBlur(grayScaleImage, 5)

    ReSized3 = cv2.resize(smoothGrayScale, (960, 540))

    #plt.imshow(ReSized3, cmap='gray')

    #retrieving the edges for cartoon effect

    #by using thresholding technique

    getEdge = cv2.adaptiveThreshold(smoothGrayScale, 255, 

        cv2.ADAPTIVE_THRESH_MEAN_C, 

        cv2.THRESH_BINARY, 9, 9)

    ReSized4 = cv2.resize(getEdge, (960, 540))

    #plt.imshow(ReSized4, cmap='gray')

    #applying bilateral filter to remove noise 

    #and keep edge sharp as required

    colorImage = cv2.bilateralFilter(originalmage, 9, 300, 300)

    ReSized5 = cv2.resize(colorImage, (960, 540))

    #plt.imshow(ReSized5, cmap='gray')

    #masking edged image with our "BEAUTIFY" image

    cartoonImage = cv2.bitwise_and(colorImage, colorImage, mask=getEdge)

    ReSized6 = cv2.resize(cartoonImage, (960, 540))

    #plt.imshow(ReSized6, cmap='gray')

    # Plotting the whole transition

    images=[ReSized1, ReSized2, ReSized3, ReSized4, ReSized5, ReSized6]

    fig, axes = plt.subplots(3,2, figsize=(8,8), subplot_kw={'xticks':[], 'yticks':[]}, gridspec_kw=dict(hspace=0.1, wspace=0.1))

    for i, ax in enumerate(axes.flat):

        ax.imshow(images[i], cmap='gray')

    save1=Button(top,text="Save cartoon image",command=lambda: save(ReSized6, ImagePath),padx=30,pady=5)

    save1.configure(background='#364156', foreground='white',font=('calibri',10,'bold'))

    save1.pack(side=TOP,pady=50)

    

    plt.show()

    

    

def save(ReSized6, ImagePath):

    #saving an image using imwrite()

    newName="cartoonified_Image"

    path1 = os.path.dirname(ImagePath)

    extension=os.path.splitext(ImagePath)[1]

    path = os.path.join(path1, newName+extension)

    cv2.imwrite(path, cv2.cvtColor(ReSized6, cv2.COLOR_RGB2BGR))

    I= "Image saved by name " + newName +" at "+ path

    tk.messagebox.showinfo(title=None, message=I)

upload=Button(top,text="Cartoonify an Image",command=upload,padx=10,pady=5)

upload.configure(background='#364156', foreground='white',font=('calibri',10,'bold'))

upload.pack(side=TOP,pady=50)

top.mainloop()