How to Urlretrieve and crop image based on data from CSV file? - pandas

Question

I have a CSV file with url's and box coordinates (x coordinate of the top left corner, y coordinate of the top left corner, x coordinate of the bottom right corner and y coordinate of the bottom right corner) and I would like to acquire the image, crop it based on the coordinates (to 256x256) and then save the image. Unfortunately a solution to download the whole database and then create a separate with cropped images is difficult due to the size of the database. That for, it is necessary to create the image database with cropped images from the beginning. Another way is to save the image and then subsequently crop it and rewrite the initial image (and then i += 1 iterate to the next one).
Would the current approach work or should I use a different method for it? Additonally, how would I save the acquired images to a specified folder, as currently it downloads to the same folder as the script.
import urllib.request
import csv
import numpy as np
import pandas as pd
from io import BytesIO
import requests
from PIL import Image
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
filename = "images"
# open file to read
with open("data_test.csv".format(filename), 'r') as csvfile:
reader = csv.reader(csvfile)
# pop header row (1st row in csv)
header = next(reader)
# iterate on all lines
i = 0
for line in csvfile:
splitted_line = line.split(',')
# check if we have an image URL
if splitted_line[1] != '' and splitted_line[1] != "\n":
response = requests.get(splitted_line[1])
img = Image.open(BytesIO(response.content))
#crop_img = img[splitted_line[2]:splitted_line[3], splitted_line[4]:splitted_line[5]]
#crop_img = img[315:105, 370:173]
img.save(str(i) + ".png")
#crop_img = img[105:105+173,315:315+370]
#[y: y + h, x: x + w]
new_img = img.resize((256, 256))
new_img.save(str(i) + ".png")
imgplot = plt.imshow(img)
plt.show()
# urllib.request.urlopen(splitted_line[1])
print("Image saved for {0}".format(splitted_line[0]))
# img = cv2.imread(img_path, 0)
i += 1
else:
print("No result for {0}".format(splitted_line[0]))
Any further recommendations are welcome.
Edit: The latest version gives me error :
crop_img = img[105:105+173,315:315+370]
TypeError: 'JpegImageFile' object is not subscriptable

Answer 1

I solved the problem using Bytes.IO and some cropping/resizing techniques.
import csv
from io import BytesIO
import requests
from PIL import Image
import matplotlib.pyplot as plt
filename = "images"
# open file to read
with open("data_test.csv".format(filename), 'r') as csvfile:
reader = csv.reader(csvfile)
# pop header row (1st row in csv)
header = next(reader)
# iterate on all lines
i = 0
for line in csvfile:
splitted_line = line.split(',')
# check if we have an image URL
if splitted_line[1] != '' and splitted_line[1] != "\n":
response = requests.get(splitted_line[1])
img = Image.open(BytesIO(response.content))
#im.crop(box) ⇒ 4-tuple defining the left, upper, right, and lower pixel coordinate
left_x = int(splitted_line[2])
top_y = int(splitted_line[3])
right_x = int(splitted_line[4])
bottom_y = int(splitted_line[5])
crop = img.crop((left_x, top_y, right_x, bottom_y))
new_img = crop.resize((256, 256))
"""
# preview new images
imgplot = plt.imshow(new_img)
plt.show()
"""
new_img.save(str(i) + ".png")
print("Image saved for {0}".format(splitted_line[0]))
i += 1
else:
print("No result for {0}".format(splitted_line[0]))
Hope it will help someone. Any optimization recommendations are still welcome.