![\"cartoonifier](\"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2020\/09\/cartoonifier-output.png\")
<\/a><\/p>\nLet\u2019s head toward creating something CREATIVE.<\/p>\n Original Image:<\/strong><\/p>\n Please download source code of Image Cartoonfier Project: Cartoonify an Image in Python<\/strong><\/a><\/p>\n We will import the following modules:<\/p>\n Code:<\/strong><\/p>\n In this step, we will build the main window of our application, where the buttons, labels, and images will reside. We also give it a title by title() function.<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n The above code opens the file box, i.e the pop-up box to choose the file from the device, which opens every time you run the code. fileopenbox() is the method in easyGUI module which returns the path of the chosen file as a string.<\/p>\n NOTE:<\/strong><\/em> Now, all the operation will be done on the button click, thus all the below steps are the part of function cartoonify (ImagePath)<\/p>\n Now, just think, how will a program read an image? For a computer, everything is just numbers. Thus, in the below code, we will convert our image into a numpy array.<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n Imread is a method in cv2 which is used to store images in the form of numbers. This helps us to perform operations according to our needs. The image is read as a numpy array, in which cell values depict R, G, and B values of a pixel.<\/p>\n NOTE:<\/strong><\/em> We resize the image after each transformation to display all the images on a similar scale at last.<\/p>\n Beginning with image transformations:<\/strong><\/p>\n 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 color image and mask it with edges. This creates a beautiful cartoon image with edges and lightened color of the original image.<\/p>\n Let\u2019s start with these transformations to convert an image to its cartoon image.<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n cvtColor(image, flag) is a method in cv2 which is used to transform an image into the colour-space mentioned as \u2018flag\u2019. 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.<\/p>\n After each transformation, we resize the resultant image using the resize() method in cv2 and display it using imshow() method. This is done to get more clear insights into every single transformation step.<\/p>\n The above code will generate the following output:<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n 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.<\/p>\n The above code generates the following output:<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n Cartoon effect has two specialties:<\/p>\n 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 the block size.<\/p>\n The above code will generate output like below:<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n In the above code, we finally work on the second specialty. We prepare a lightened color image that we mask with edges at the end to produce a cartoon image. We use bilateralFilter which removes the noise. It can be taken as smoothening of an image to an extent.<\/p>\n The third parameter is the diameter of the pixel neighborhood, i.e, the number of pixels around a certain pixel which will determine its value. The fourth and Fifth parameter defines signmaColor and sigmaSpace. These parameters are used to give a sigma effect, i.e make an image look vicious and like water paint, removing the roughness in colors.<\/p>\n Yes, it\u2019s similar to BEAUTIFY or AI effect in cameras of modern mobile phones.<\/p>\n The above code generates the following output:<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n So, let’s combine the two specialties. This will be done using MASKING. We perform bitwise and on two images to mask them. Remember, images are just numbers?<\/p>\n Yes, so that\u2019s how we mask edged image on our \u201cBEAUTIFY\u201d image.<\/p>\n This finally CARTOONIFY our image!<\/p>\n The above code will generate output like below:<\/p>\n Code:<\/strong><\/p>\n Explanation:<\/strong><\/p>\n To plot all the images, we first make a list of all the images. The list here is named \u201cimages\u201d 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.<\/p>\n plt.show() plots the whole plot at once after we plot on each subplot.<\/p>\n The above code will generate output like below:<\/p>\n <\/p>\n Explanation:<\/strong><\/p>\n Here, the 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.<\/p>\n 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.<\/p>\n Here, newName stores \u201cCartoonified_Image\u201d 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.<\/p>\n 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.<\/p>\n Once executed with button, this function will result in below output:<\/p>\n The above code makes a button as soon as the image transformation is done. It gives an option to the user to save cartoonified image.<\/p>\n<\/a><\/p>\n<\/a><\/p>\nSteps to develop Image Cartoonifier<\/h3>\n
Download Image Cartoonifies Code<\/h3>\n
1: Importing the required modules<\/h4>\n
\n
import cv2 #for image processing\r\nimport easygui #to open the filebox\r\nimport numpy as np #to store image\r\nimport imageio #to read image stored at particular path\r\nimport sys\r\nimport matplotlib.pyplot as plt\r\nimport os\r\nimport tkinter as tk\r\nfrom tkinter import filedialog\r\nfrom tkinter import *\r\nfrom PIL import ImageTk, Image\r\n<\/pre>\n
2: Building a File Box to choose a particular file<\/h4>\n
\"\"\" fileopenbox opens the box to choose file\r\nand help us store file path as string \"\"\"\r\ndef upload():\r\n ImagePath=easygui.fileopenbox()\r\n cartoonify(ImagePath)\r\n<\/pre>\n
def cartoonify(ImagePath):<\/pre>\n
3: How is an image stored?<\/h4>\n
#read the image\r\n originalmage = cv2.imread(ImagePath)\r\n originalmage = cv2.cvtColor(originalmage, cv2.COLOR_BGR2RGB)\r\n#print(image) # image is stored in form of numbers\r\n\r\n# confirm that image is chosen\r\n if originalmage is None:\r\n print(\"Can not find any image. Choose appropriate file\")\r\n sys.exit()\r\n\r\n ReSized1 = cv2.resize(originalmage, (960, 540))\r\n#plt.imshow(ReSized1, cmap='gray')\r\n<\/pre>\n
4: Transforming an image to grayscale<\/h4>\n
#converting an image to grayscale\r\ngrayScaleImage = cv2.cvtColor(originalmage, cv2.COLOR_BGR2GRAY)\r\nReSized2 = cv2.resize(grayScaleImage, (960, 540))\r\n#plt.imshow(ReSized2, cmap='gray')\r\n<\/pre>\n
<\/a><\/p>\n5: Smoothening a grayscale image<\/h4>\n
#applying median blur to smoothen an image\r\nsmoothGrayScale = cv2.medianBlur(grayScaleImage, 5)\r\nReSized3 = cv2.resize(smoothGrayScale, (960, 540))\r\n#plt.imshow(ReSized3, cmap='gray')\r\n<\/pre>\n
<\/a><\/p>\n6: Retrieving the edges of an image<\/h4>\n
#retrieving the edges for cartoon effect\r\n#by using thresholding technique\r\ngetEdge = cv2.adaptiveThreshold(smoothGrayScale, 255, \r\n cv2.ADAPTIVE_THRESH_MEAN_C, \r\n cv2.THRESH_BINARY, 9, 9)\r\n\r\nReSized4 = cv2.resize(getEdge, (960, 540))\r\n#plt.imshow(ReSized4, cmap='gray')\r\n<\/pre>\n
\n
<\/a><\/p>\n7: Preparing a Mask Image<\/h4>\n
#applying bilateral filter to remove noise \r\n#and keep edge sharp as required\r\ncolorImage = cv2.bilateralFilter(originalmage, 9, 300, 300)\r\nReSized5 = cv2.resize(colorImage, (960, 540))\r\n#plt.imshow(ReSized5, cmap='gray')\r\n<\/pre>\n
<\/a><\/p>\n8: Giving a Cartoon Effect<\/h4>\n
#masking edged image with our \"BEAUTIFY\" image\r\ncartoonImage = cv2.bitwise_and(colorImage, colorImage, mask=getEdge)\r\n\r\nReSized6 = cv2.resize(cartoonImage, (960, 540))\r\n#plt.imshow(ReSized6, cmap='gray')\r\n<\/pre>\n
<\/a><\/p>\n9: Plotting all the transitions together<\/h4>\n
# Plotting the whole transition\r\nimages=[ReSized1, ReSized2, ReSized3, ReSized4, ReSized5, ReSized6]\r\nfig, axes = plt.subplots(3,2, figsize=(8,8), subplot_kw={'xticks':[], 'yticks':[]}, gridspec_kw=dict(hspace=0.1, wspace=0.1))\r\nfor i, ax in enumerate(axes.flat):\r\n ax.imshow(images[i], cmap='gray')\r\n\/\/save button code\r\nplt.show()\r\n<\/pre>\n<\/a><\/p>\n10: Functionally of save button<\/h4>\n
def save(ReSized6, ImagePath):\r\n #saving an image using imwrite()\r\n newName=\"cartoonified_Image\"\r\n path1 = os.path.dirname(ImagePath)\r\n extension=os.path.splitext(ImagePath)[1]\r\n path = os.path.join(path1, newName+extension)\r\n cv2.imwrite(path, cv2.cvtColor(ReSized6, cv2.COLOR_RGB2BGR))\r\n I = \"Image saved by name \" + newName +\" at \"+ path\r\n tk.messagebox.showinfo(title=None, message=I)\r\n<\/pre>\n
<\/a><\/p>\n11: Making the main window<\/h4>\n
top=tk.Tk()\r\ntop.geometry('400x400')\r\ntop.title('Cartoonify Your Image !')\r\ntop.configure(background='white')\r\nlabel=Label(top,background='#CDCDCD', font=('calibri',20,'bold'))\r\n<\/pre>\n12: Making the Cartoonify button in the main window<\/h4>\n
upload=Button(top,text=\"Cartoonify an Image\",command=upload,padx=10,pady=5)\r\nupload.configure(background='#364156', foreground='white',font=('calibri',10,'bold'))\r\nupload.pack(side=TOP,pady=50)\r\n<\/pre>\n<\/a><\/p>\n13: Making a Save button in the main window<\/h4>\n
save1=Button(top,text=\"Save cartoon image\",command=lambda: save(ImagePath, ReSized6),padx=30,pady=5)\r\nsave1.configure(background='#364156', foreground='white',font=('calibri',10,'bold'))\r\nsave1.pack(side=TOP,pady=50)\r\n<\/pre>\n<\/a><\/p>\n14: Main function to build the tkinter window<\/h4>\n
top.mainloop()<\/pre>\n