Optimization of basic image processing in Python

Question

I'm trying to accomplish a basic image processing. Here is my algorithm :

Find n., n+1., n+2. pixel's RGB values in a row and create a new image from these values.

Here is my example code in python :

import glob
import ntpath
import time
from multiprocessing.pool import ThreadPool as Pool

import matplotlib.pyplot as plt
import numpy as np
from PIL import Image

images = glob.glob('model/*.png')
pool_size = 17


def worker(image_file):
    try:
        new_image = np.zeros((2400, 1280, 3), dtype=np.uint8)
        image_name = ntpath.basename(image_file)
        print(f'Processing [{image_name}]')

        image = Image.open(image_file)
        data = np.asarray(image)

        for i in range(0, 2399):
            for j in range(0, 1279):
                pix_x = j * 3 + 1
                red = data[i, pix_x - 1][0]
                green = data[i, pix_x][1]
                blue = data[i, pix_x + 1][2]
                new_image[i, j] = [red, green, blue]

        im = Image.fromarray(new_image)
        im.save(f'export/{image_name}')
    except:
        print('error with item')


pool = Pool(pool_size)
for image_file in images:
    pool.apply_async(worker, (image_file,))

pool.close()
pool.join()

My input and output images are in RGB format. My code is taking 5 second for every image. I'm open for any idea to optimization this task.

Here is example input and output images :

Input Image 2 [ 3840 x 2400 ]

Output Image 3 [ 1280 x 2400 ]

This is well answered by @Lukáš-Lalinský [link]stackoverflow.com/questions/29581014/…, you want to avoid per-pixel loops in Python. They will always be slow. To get somewhat fast image processing, you need to get used to working with matrices instead of individual pixels. You have basically two options, you can either use NumPy or OpenCV, or a combination of the two... — Raw Bit Rabbit
– Raw Bit Rabbit, Commented Sep 23, 2020 at 11:10
So your output image is 1/3 width and 1/3 the height of your input image? Please show input and output images. — Mark Setchell
– Mark Setchell, Commented Sep 23, 2020 at 11:53

Mark Setchell · Accepted Answer · 2020-09-23 12:16:20Z

1

Here is an approach:

import cv2
import numpy as np

# Load input image
im = cv2.imread('input.png')

# Calculate new first layer - it is every 3rd pixel of the first layer of im
n1 = im[:, ::3, 0]

# Calculate new second layer - it is every 3rd pixel of the second layer of im, starting with an offset of 1 pixel
n2 = im[:, 1::3, 1]

# Calculate new third layer - it is every 3rd pixel of the third layer of im, starting with an offset of 2 pixels
n3 = im[:, 2::3, 2]

# Now stack the three new layers to make a new output image
res = np.dstack((n1,n2,n3))

edited Sep 23, 2020 at 12:16

answered Sep 23, 2020 at 11:59

Mark Setchell

210k32 gold badges310 silver badges504 bronze badges

Sign up to request clarification or add additional context in comments.

4 Comments

Kubilay Sacikara Over a year ago

dstack is compression on both axis. is it possible to compress only one axis ?

Mark Setchell Over a year ago

hstack appends images side-by-side horizontally. vstack appends images one above the other vertically. dstack stacks images by channels, or depthwise. No compression involved. It is the same as np.stack(..., axis=2, ...)

Mark Setchell Over a year ago

By the way, if you are happier writing loops, you could look at numba, example here stackoverflow.com/a/55356126/2836621

Mark Setchell Over a year ago

By the way, threads don't buy you much with Python as, apart from I/O, only one thread will be active at a time because of the GIL. You may therefore want multiprocessing rather than multithreading. Try watching your CPUs with htop or Process Monitor while processing to see if all cores are 100% busy.

Prefect · Accepted Answer · 2020-09-25 13:22:41Z

As far as I understood from the question, you want to shift the pixel values of each channel of the input image in the output image. So, here is my approach.

im = cv2.cvtColor(cv2.imread('my_image.jpg'), cv2.COLOR_BGR2RGB)
im = np.pad(im, [(3, 3),(3,3),(0,0)], mode='constant', constant_values=0) # Add padding for enabling the shifting process later

r= im[:,:,0]

g= im[:,:,1]
g = np.delete(g,np.s_[-1],axis=1) # remove the last column
temp_pad = np.zeros(shape=(g.shape[0],1)) # removed part
g = np.concatenate((temp_pad,g),axis=1) # put the removed part back


b = im[:,:,2]
b = np.delete(b,np.s_[-2::],axis=1) # remove the last columns
temp_pad = np.zeros(shape=(b.shape[0],2)) # removed parts
b = np.concatenate((temp_pad,b),axis=1) # put the removed parts back


new_im = np.dstack((r,g,b)) # Merge the channels
new_im = new_im[3:-3,3:-3,:]/np.amax(new_im)#*255 # Remove the padding

Basically, I achieved the shifting by padding&merging the green and blue channels. Let me know if this is what you are looking for. Kolay gelsin :)

Collectives™ on Stack Overflow

Optimization of basic image processing in Python

2 Answers 2

4 Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

4 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related