Limiting the amount of images from to be loaded from a folder - python

I have 50 images inside a folder, but for testing i'll need to choose between different sizes, for instance sometimes ill need just 10 images from the folder, and some times ill need 11 or 15. But what i am doing right now is loading all images inside a given folder path. Which in turn, would make me create a new folder with the desired amount of images i would like to load a different amount of images, which is optimal.
This is the current way im doing to load all images:
def loadImages(path):
imagesList = listdir(path)
loadedImages = []
for image in imagesList:
img = PImage.open(path + image)
arr = np.array(img)
loadedImages.append(arr)
return loadedImages
Then i'd go and do
images = loadImages('imgfolder'), which would load everything inside the folder, when i just want the amount i really need.

You could add a second parameter to the funcion, which is the maximum size in MegaByte:
import os
import numpy as np
from PIL import Image
def loadImages(path, max_size):
imagesList = os.listdir(path)
loadedImages = []
temp_size = 0
for image in imagesList:
os.chdir(path)
temp_size += os.path.getsize(image)
if temp_size > max_size*1000000:
break
img = Image.open(path + image)
arr = np.array(img)
loadedImages.append(arr)
return loadedImages
loadImages(path, 50)
If you want to set the number of pictures you can add a second parameter as max_num:
def loadImages(path, max_num):
imagesList = listdir(path)
loadedImages = []
for i, image in enumerate(imagesList):
if i == max_num:
break
img = PImage.open(path + image)
arr = np.array(img)
loadedImages.append(arr)
return loadedImages
loadImages(path, 10)

Related

Loop over images in directories/Subdirectories for data processing

I am trying to do image processing on my dataset. The dataset is divided into 346 folders according to the following manner
What I want to do is
loop over the 346.
Enter each folder and process the images within
Process the image in regards to changing it to gray scale, resize and normalize (these three steps should be applied to my whole dataset.
I want to keep the same folders/files names and dont change it when I run my data processing.
The folder/ files name are as follows
video_0001/ 00000.png, 00001.png, .....
video_0002/ 00000.png, 00001.png,
The number of files vary according to each folder and the last video_0346
P.S when I try to normalize the images I get black images when dividing by 255
I am still new to python. Here's what I was able to accomplish
I appreciate your help
Img_height = 512
Img_width = 512
srcdir = "C:\\Users\\Desktop\\_dataset"
for subdir, dirs, files in os.walk(srcdir):
for i in range(346):
for file in os.listdir(subdir):
print(file )
img = cv2.imread(os.path.join(srcdir,file))
print("image", img)
gray_img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
Image_sample_resized = resize(gray_img, (height, width))
plt.imshow( Image_sample_resized, cmap = "gray")
i = i+1
I was still trying to understand how you wanted to save you formated images but the methods below just save them to a new dir that you specify so you can batch them while training if you want.
import os
import cv2
import matplotlib.image as mpimg
def resize_image(image, size=(512, 512)):
"""
Resize an image to a fixed size
"""
return cv2.resize(image, size)
def convert_to_grayscale(image):
"""
Convert an image to grayscale
"""
return cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
def normalize_image(image):
"""
Normalize an image
"""
return cv2.normalize(image, None, 0, 255, cv2.NORM_MINMAX)
def save_image(image, directory, filename):
"""
Save an image to a new directory
"""
cv2.imwrite(os.path.join(directory, filename), image)
def main():
"""
Main function
"""
# Get the directory to process
directory = input("Enter the directory to process: ")
# Get the directory to save the images
save_directory = input("Enter the directory to save the images: ")
# Size to resize the images
img_width, img_height = 512, 512
# Iterate through the directory
for root, _, files in os.walk(directory):
for file in files:
# Get the filepath
filepath = os.path.join(root, file)
# Get the filename
filename = os.path.basename(filepath)
# Get the extension
extension = os.path.splitext(filepath)[1]
# Check if the file is an image
if extension in [".jpg", ".jpeg", ".png"]:
# Load the image
image = mpimg.imread(filepath)
# Resize the image
image = resize_image(image, (img_width, img_height))
# Convert the image to grayscale
image = convert_to_grayscale(image)
# Normalize the image
image = normalize_image(image)
# Save the image
save_image(image, save_directory, filename)
if __name__ == "__main__":
main()

How would I read a folder of images on my computer into a dataframe on Jupyter Notebooks?

This is my code right now, I have used a for loop to go through all the images in the folder and use the PIL library to read it into an array.
import cv2
import os
folder = '/Users/x/x/x/x'
def load_images_from_folder(folder):
images = []
for filename in os.listdir(folder):
img = cv2.imread(os.path.join(folder,filename))
if img is not None:
images.append(img)
return images
img = Image.fromarray(images_array,'RGB', dtype = object)

How do I loop this Python PIL code to repeat with different images?

I have the following code that uses PIL to paste an image on top on another.
I want to repeat this process to do it automatically with 1000+ images. Is there a way to loop it by choosing 1000+ images from a folder and pasting them on top of another 1000+ images from another folder?
from PIL import Image, ImageOps
img = Image.open('image1.png', 'r')
img_w, img_h = img.size
background = Image.open('image2.png', 'r')
bg_w, bg_h = background.size
offset = ((bg_w - img_w) // 1, (bg_h - img_h) // 6)
background.paste(img, offset)
background.save('out.png')
My interpretation is that you want all images in one folder to go over all images in another folder.
You need to itr over all the file in your directories and except IOError in case that there isn't it supported image file you've itr'd over.
You will need to import os, and filename the image is saved as is the iteration number.
This is what your code would look like:
from PIL import Image, ImageOps
import os
dir = "C:/Users/User/Pictures/"
dir2 = "C:/Users/User/Pictures/"
images = os.listdir(dir)
images2 = os.listdir(dir2)
itr = 1
for image in images:
for image2 in images2:
try:
img = Image.open(dir + image, 'r')
img_w, img_h = img.size
background = Image.open(dir + image2, 'r')
print("Image = " + image + " background = " + image2 + " at itr "+ str(itr))
print("")
bg_w, bg_h = background.size
offset = ((bg_w - img_w) // 1, (bg_h - img_h) // 6)
background.paste(img, offset)
background.save('./How do I loop this Python PIL code/' + str(itr)+ ".png")
itr += 1
except IOError:
pass

How to read multiple image from different folders using python with Opencv

I am trying to read multiple images from 3 different folder. Each folder contain 100 images. I try 2 different code but I have no idea why the codes does not work. Anyone can help? Thanks
For example:
Cropped Matrix:Matrix1.png, Matrix2.png,...
Cropped Marks:Mark1.png, Mark2.png,...
Cropped Marks1:Mark1Q1.png, Mark1Q2.png,...
Output: Matrix1.png + Mark1.png + Mark1Q1.png
Code 1:
#1st
path1 = os.path.abspath("C:/Users/TSL/Desktop/Crop/Cropped Matrix/*.png")
path2 = os.path.abspath("C:/Users/TSL/Desktop/Crop/Cropped Marks/*.png")
path3 = os.path.abspath("C:/Users/TSL/Desktop/Crop/Cropped Marks1/*.png")
folder= os.path.join(path1, path2, path3)
def load(folder):
images = []
for filename in os.listdir(folder):
if filename.endswith(".png"):
img = cv2.imread(os.path.join(folder, filename))
if img is not None:
images.append(img)
return images
root = 'C:/Users/TSL/Desktop/Crop'
folders = [os.path.join(root, x) for x in ('Cropped Matrix', 'Cropped Marks', 'Cropped Marks1')]
all = [img for folder in folders for img in load(folder)]
cv2.imshow("Join img", all)
cv2.waitKey(0)
Code 2
#2nd
path1 = os.path.abspath('Cropped Matrix')
path2 = os.path.abspath('Cropped Marks')
path3 = os.path.abspath('Cropped Marks1')
folder= os.path.join(path1, path2, path3)
def load(folder):
images = []
for filename in os.listdir(folder):
if any([filename.endswith(x) for x in [".png"]]):
img = cv2.imread(os.path.join(folder, filename))
if img is not None:
images.append(img)
return images
folders = ['Cropped Matrix', 'Cropped Marks',]
for folder in folders:
images = load(folder)
read = cv2.imread(images)
cv2.imshow("Join images", read)
cv2.waitKey(0)
all is a list of images and you try to show it using imshow. To show all images one by one you can loop through all and show each with imshow.
Also, as #gold_cy correctly points out, all is a built in python function, so you should avoid using it as a variable name. Change it to something like all_images.
all_images = [img for folder in folders for img in load(folder)]
for i in all_images:
cv2.imshow("Image", i) #or however you want
cv2.waitKey(10) #or any suitable number

Save images having target objects from 1 folder to another after detecting target and non-target objects from the frames

Images from 1st folder are getting repeated along with images from 2nd folder while saving to the destination directory
I have made the code to identify target and non-target objects from images and save the images having my target object to a folder. Below is my code
def target_non_target(input_frames_folder,model_file,output):
if not os.path.exists(output):
os.makedirs(output,exist_ok=True)
count=0
folders = glob(input_frames_folder)
img_list = []
for folder in folders:
folder_name=os.path.basename(folder)
print(folder_name)
out_path = output +"\\" + folder_name
os.makedirs(out_path,exist_ok=True)
for f in glob(folder+"/*.jpg"):
img_list.append(f)
for i in range(len(img_list)):
v1=os.path.basename(img_list[i])
img_name = os.path.splitext(v1)[0]
image = cv2.imread(img_list[i])
orig = image.copy()
image = cv2.resize(image, (28, 28))
image = image.astype("float") / 255.0
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
print("[INFO] loading network...")
model = load_model(model_file)
(non_target, target) = model.predict(image)[0]
if target > non_target:
label = "Target"
else:
label = "Non Target"
probab = target if target > non_target else non_target
label = "{}: {:.2f}%".format(label, probab * 100)
op = imutils.resize(orig, width=400)
cv2.putText(op, label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX,0.7, (0, 255, 0), 2)
if target > non_target:
cv2.imwrite(out_path+"/"+"\\{}.jpg".format(img_name),orig)
cv2.waitKey(0)
#return target_op
frames_folder = ("C:\\Python36\\videos\\videos_new\\*")
model = ("C:\\Python35\\target_non_target\\target_non_target.model")
output_folder = ("C:\\Python35\\target_non_target\\Target_images_new")
target_check = target_non_target(frames_folder,model,output_folder)
Suppose there are 2 folders A and B in 2 different drives like Drive C and Drive D. Target images read from folder A of C Drive need to be saved in folder A of D drive. Target images from folder B of C Drive need to be saved in folder B of D Drive. This is working but images from folder A of D drive are getting repeated in folder B of D Drive which should not happen. Can someone guide me what changes shall be made for getting the desired results?
Of course Python offers all the tools you need. To copy files, you can use shutil.copy(). To find all JPEG files in the source directory, you can use glob.iglob().
import glob
import shutil
import os
src_dir = "your/source/dir"
dst_dir = "your/destination/dir"
for jpgfile in glob.iglob(os.path.join(src_dir, "*.jpg")):
shutil.copy(jpgfile, dst_dir)

Categories