Image Captioning using Python

Last Updated : 16 Nov, 2022

Image captioning is a very classical and challenging problem coming to Deep Learning domain, in which we generate the textual description of image using its property, but we will not use Deep learning here. In this article, we will simply learn how can we simply caption the images using PIL. Preprocessing on images is a great utility provided by Python PIL library. Not only we can change size, mode, orientation but we can draw on images, write text over it as well. Install the required libraries:

urllib requests PIL glob shutil

Steps to follow first –

Download the font.ttf file (before running the code) using this link.
Make folder with name as “CaptionedImages” beforehand where the output captioned images will be stored.

Below is the stepwise implementation using Python: Step #1:

Python3

# importing required libraries
import urllib
import requests
import os
 
# retrieving using image url 
urllib.request.urlretrieve("https://i.ibb.co/xY4DJJ5/img1.jpg", "img1.jpg")
urllib.request.urlretrieve("https://i.ibb.co/Gnd1Y1L/img2.jpg", "img2.jpg")
urllib.request.urlretrieve("https://i.ibb.co/Z6JgS1L/img3.jpg", "img3.jpg")
 
print('Images downloaded')
 
# get current working directory path
path = os.getcwd()
 
 
captionarr = [
    "This is the first caption",
    "This is the second caption",
    "This is the third caption"
    ]

Step #2:

Python3

# importing necessary functions from PIL
from PIL import Image
from PIL import ImageFont
from PIL import ImageDraw 
 
# print(os.getcwd())
 
# checking the file mime types if
# it is jpg, png or jpeg
def ext(file):
    index = file.find(".jpg")
    current_file = ""
    current_file = file[index:]
    return current_file 
 
def ext2(file):
    index = file.find(".jpeg")
    current_file = ""
    current_file = file[index:]
    return current_file 
 
def ext3(file):
    index = file.find(".png")
    current_file = ""
    current_file = file[index:]
    return current_file 
 
 
# converting text from lowercase to uppercase
def convert(words):
    s = ""
    for word in words:
        s += word.upper() 
    return s
 
caption_first = convert(captionarr[0])
caption_second = convert(captionarr[1])
caption_third = convert(captionarr[2])
     
print(caption_first)
print(caption_second)
print(caption_third)
 
 
count = 0
 
for f in os.listdir('.'):
    try:
        # Checking for file types if jpg, png
        # or jpeg excluding other files
        if (ext(f) == '.jpg' or ext2(f) == '.jpeg' or ext3(f) == '.png'):
            img = Image.open(f) 
            width, height = img.size
            basewidth = 1200
            # print(height)
 
            # Resizing images to same width height
            wpercent = (basewidth / float(img.size[0]))
            hsize = int((float(img.size[1])*float(wpercent)))
            img = img.resize((basewidth, hsize), Image.ANTIALIAS)
            new_width, new_height = img.size
 
 
            # print(new_height)
            # changing image mode if not in RGB
            if not img.mode == 'RGB':
                img = img.convert('RGB')
         
            draw = ImageDraw.Draw(img)
            # font = ImageFont.truetype(<font-file>, <font-size>)
            # initializing which font will be chosen by us
            font = ImageFont.truetype("Arial Bold.ttf", 35) 
             
             # First Caption on First image
            if count == 0:
                draw.text((new_width / 15 + 25, new_height - 100),
                           caption_first, (255, 0, 0), font = font,
                           align ="center")
                            
            # Second Caption on Second image
            elif count == 1: 
                draw.text((new_width / 15 + 25, new_height - 100),
                          caption_second, (255, 0, 0), font = font,
                          align ="center")
                                                   
            # Third Caption on Third image
            else: 
                draw.text(( new_width / 15 + 25, new_height - 100),
                            caption_third, (255, 0, 0), font = font,
                            align ="center")             
 
            img.save("CaptionedImges/{}".format(f))     
            print('done')
            count = count + 1
             
    except OSError:
        pass

Step #3: Sorting the output files in accordance to last modified time so that they do not get placed in alphabetical or any other mismanaged order.

Python3

import os
import glob
import shutil
 
# changing directory to CaptionedImages
os.chdir(".\\CaptionedImges") 
 
fnames = []
for file in os.listdir('.'):
    # appending files in directory to the frames arr
    fnames.append(file) 
 
# sorting the files in frames array 
# on the basis of last modified time
# reverse = True means ascending order sorting
fnames.sort(key = lambda x: os.stat(x).st_ctime, reverse = True)

Output:

Adding Text on Image using Python - PIL

md1844

Improve

Article Tags :

Practice Tags :

python

Image Captioning using Python

Python3

Python3

Python3

Similar Reads