I would like to slice up an image in python
and paste it back together again as a window.
The tiles measure as 8pixels by 9pixels and each row needs to skip 1 pixel
I would then need to merge the tiles back together again with a 1 pixel padding around each tile to give a windowed effect.
The image is black and white but for the example I have used color to show that the windowed effect would need to have a white background
input example
Desired Output
Update: change tiles dimension to bigger for illustration, you can adjust per your need
Use this:
import cv2
image = cv2.imread('test.jpg')
tiles_height = 50
tiles_width = 30
# white padding
padding_x = 10
padding_y = 20
num_y = int(image.shape[0]/tiles_height)
num_x = int(image.shape[1]/tiles_width)
new_img = np.full((image.shape[0] + num_y*padding_y, image.shape[1] + num_x*padding_x,3),255)
for incre_i,i in enumerate(range(0,image.shape[0],tiles_height)):
for incre_j,j in enumerate(range(0, image.shape[1], tiles_width)):
new_img[i+incre_i*padding_y:i+tiles_height+incre_i*padding_y
,j+incre_j*padding_x:j+tiles_width+incre_j*padding_x,:] = image[i:i+tiles_height,j:j+tiles_width,:]
cv2.imwrite('res.jpg',new_img)
print(image.shape, new_img.shape)
Update 1:
Because you want to latter remove tiles, I added code that can help you with that. Now all you have to do is changing variables in tiles config, white padding, tile index to be removed:
import cv2
image = cv2.imread('test.jpg')
# tiles config
tiles_height = 50
tiles_width = 30
# white padding
padding_x = 10
padding_y = 20
# tile index to be removed
remove_indices = [(0,0),(3,6)]
num_y = int(image.shape[0]/tiles_height)
num_x = int(image.shape[1]/tiles_width)
new_img = np.full((image.shape[0] + num_y*padding_y, image.shape[1] + num_x*padding_x,3),255)
for incre_i,i in enumerate(range(0,image.shape[0],tiles_height)):
for incre_j,j in enumerate(range(0, image.shape[1], tiles_width)):
if (incre_i,incre_j) in remove_indices:
new_img[i+incre_i*padding_y:i+tiles_height+incre_i*padding_y
,j+incre_j*padding_x:j+tiles_width+incre_j*padding_x,:] = 255
else:
new_img[i+incre_i*padding_y:i+tiles_height+incre_i*padding_y
,j+incre_j*padding_x:j+tiles_width+incre_j*padding_x,:] = image[i:i+tiles_height,j:j+tiles_width,:]
cv2.imwrite('remove_tiles.jpg',new_img)
print(image.shape, new_img.shape)
test.jpg
res.jpg
remove_tiles.jpg
print(image.shape, new_img.shape) gives (952, 1429, 3) (1332, 1899, 3)
You can try with skimage.utils.view_as_windows from the scikit-image package:
from skimage.util import view_as_windows
import matplotlib.pyplot as plt
import numpy as np
img = np.random.rand(90, 90, 1) # gray-scale image, you can change the channels accordingly
img[8::9,] = 0
tiles = view_as_windows(img, (9, 9, 1), (9, 9, 1)).squeeze(2) # squeeze out unneded dim
tiles = tiles[:, :, :-1, :, :] # Remove last row of each tile
# plot the original image
plt.axis("off")
plt.imshow(img.squeeze(2))
plt.show()
# plot the tiles
fig, axes = plt.subplots(10, 10)
for i in range(10):
for j in range(10):
axes[i, j].axis("off")
axes[i, j].imshow(tiles[i, j, ...].squeeze(-1))
plt.show()
Here is the result:
Original
Sliced
The torch.Tensor.unfold operator from PyTorch could be an option too.
How can I overlay a transparent PNG onto another image without losing it's transparency using openCV in python?
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png')
# Help please
cv2.imwrite('combined.png', background)
Desired output:
Sources:
Background Image
Overlay
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png')
added_image = cv2.addWeighted(background,0.4,overlay,0.1,0)
cv2.imwrite('combined.png', added_image)
The correct answer to this was far too hard to come by, so I'm posting this answer even though the question is really old. What you are looking for is "over" compositing, and the algorithm for this can be found on Wikipedia: https://en.wikipedia.org/wiki/Alpha_compositing
I am far from an expert with OpenCV, but after some experimentation this is the most efficient way I have found to accomplish the task:
import cv2
background = cv2.imread("background.png", cv2.IMREAD_UNCHANGED)
foreground = cv2.imread("overlay.png", cv2.IMREAD_UNCHANGED)
# normalize alpha channels from 0-255 to 0-1
alpha_background = background[:,:,3] / 255.0
alpha_foreground = foreground[:,:,3] / 255.0
# set adjusted colors
for color in range(0, 3):
background[:,:,color] = alpha_foreground * foreground[:,:,color] + \
alpha_background * background[:,:,color] * (1 - alpha_foreground)
# set adjusted alpha and denormalize back to 0-255
background[:,:,3] = (1 - (1 - alpha_foreground) * (1 - alpha_background)) * 255
# display the image
cv2.imshow("Composited image", background)
cv2.waitKey(0)
The following code will use the alpha channels of the overlay image to correctly blend it into the background image, use x and y to set the top-left corner of the overlay image.
import cv2
import numpy as np
def overlay_transparent(background, overlay, x, y):
background_width = background.shape[1]
background_height = background.shape[0]
if x >= background_width or y >= background_height:
return background
h, w = overlay.shape[0], overlay.shape[1]
if x + w > background_width:
w = background_width - x
overlay = overlay[:, :w]
if y + h > background_height:
h = background_height - y
overlay = overlay[:h]
if overlay.shape[2] < 4:
overlay = np.concatenate(
[
overlay,
np.ones((overlay.shape[0], overlay.shape[1], 1), dtype = overlay.dtype) * 255
],
axis = 2,
)
overlay_image = overlay[..., :3]
mask = overlay[..., 3:] / 255.0
background[y:y+h, x:x+w] = (1.0 - mask) * background[y:y+h, x:x+w] + mask * overlay_image
return background
This code will mutate background so create a copy if you wish to preserve the original background image.
Been a while since this question appeared, but I believe this is the right simple answer, which could still help somebody.
background = cv2.imread('road.jpg')
overlay = cv2.imread('traffic sign.png')
rows,cols,channels = overlay.shape
overlay=cv2.addWeighted(background[250:250+rows, 0:0+cols],0.5,overlay,0.5,0)
background[250:250+rows, 0:0+cols ] = overlay
This will overlay the image over the background image such as shown here:
Ignore the ROI rectangles
Note that I used a background image of size 400x300 and the overlay image of size 32x32, is shown in the x[0-32] and y[250-282] part of the background image according to the coordinates I set for it, to first calculate the blend and then put the calculated blend in the part of the image where I want to have it.
(overlay is loaded from disk, not from the background image itself,unfortunately the overlay image has its own white background, so you can see that too in the result)
If performance isn't a concern then you can iterate over each pixel of the overlay and apply it to the background. This isn't very efficient, but it does help to understand how to work with png's alpha layer.
slow version
import cv2
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
height, width = overlay.shape[:2]
for y in range(height):
for x in range(width):
overlay_color = overlay[y, x, :3] # first three elements are color (RGB)
overlay_alpha = overlay[y, x, 3] / 255 # 4th element is the alpha channel, convert from 0-255 to 0.0-1.0
# get the color from the background image
background_color = background[y, x]
# combine the background color and the overlay color weighted by alpha
composite_color = background_color * (1 - overlay_alpha) + overlay_color * overlay_alpha
# update the background image in place
background[y, x] = composite_color
cv2.imwrite('combined.png', background)
result:
fast version
I stumbled across this question while trying to add a png overlay to a live video feed. The above solution is way too slow for that. We can make the algorithm significantly faster by using numpy's vector functions.
note: This was my first real foray into numpy so there may be better/faster methods than what I've come up with.
import cv2
import numpy as np
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
# separate the alpha channel from the color channels
alpha_channel = overlay[:, :, 3] / 255 # convert from 0-255 to 0.0-1.0
overlay_colors = overlay[:, :, :3]
# To take advantage of the speed of numpy and apply transformations to the entire image with a single operation
# the arrays need to be the same shape. However, the shapes currently looks like this:
# - overlay_colors shape:(width, height, 3) 3 color values for each pixel, (red, green, blue)
# - alpha_channel shape:(width, height, 1) 1 single alpha value for each pixel
# We will construct an alpha_mask that has the same shape as the overlay_colors by duplicate the alpha channel
# for each color so there is a 1:1 alpha channel for each color channel
alpha_mask = np.dstack((alpha_channel, alpha_channel, alpha_channel))
# The background image is larger than the overlay so we'll take a subsection of the background that matches the
# dimensions of the overlay.
# NOTE: For simplicity, the overlay is applied to the top-left corner of the background(0,0). An x and y offset
# could be used to place the overlay at any position on the background.
h, w = overlay.shape[:2]
background_subsection = background[0:h, 0:w]
# combine the background with the overlay image weighted by alpha
composite = background_subsection * (1 - alpha_mask) + overlay_colors * alpha_mask
# overwrite the section of the background image that has been updated
background[0:h, 0:w] = composite
cv2.imwrite('combined.png', background)
How much faster? On my machine the slow method takes ~3 seconds and the optimized method takes ~ 30 ms. So about
100 times faster!
Wrapped up in a function
This function handles foreground and background images of different sizes and also supports negative and positive offsets the move the overlay across the bounds of the background image in any direction.
import cv2
import numpy as np
def add_transparent_image(background, foreground, x_offset=None, y_offset=None):
bg_h, bg_w, bg_channels = background.shape
fg_h, fg_w, fg_channels = foreground.shape
assert bg_channels == 3, f'background image should have exactly 3 channels (RGB). found:{bg_channels}'
assert fg_channels == 4, f'foreground image should have exactly 4 channels (RGBA). found:{fg_channels}'
# center by default
if x_offset is None: x_offset = (bg_w - fg_w) // 2
if y_offset is None: y_offset = (bg_h - fg_h) // 2
w = min(fg_w, bg_w, fg_w + x_offset, bg_w - x_offset)
h = min(fg_h, bg_h, fg_h + y_offset, bg_h - y_offset)
if w < 1 or h < 1: return
# clip foreground and background images to the overlapping regions
bg_x = max(0, x_offset)
bg_y = max(0, y_offset)
fg_x = max(0, x_offset * -1)
fg_y = max(0, y_offset * -1)
foreground = foreground[fg_y:fg_y + h, fg_x:fg_x + w]
background_subsection = background[bg_y:bg_y + h, bg_x:bg_x + w]
# separate alpha and color channels from the foreground image
foreground_colors = foreground[:, :, :3]
alpha_channel = foreground[:, :, 3] / 255 # 0-255 => 0.0-1.0
# construct an alpha_mask that matches the image shape
alpha_mask = np.dstack((alpha_channel, alpha_channel, alpha_channel))
# combine the background with the overlay image weighted by alpha
composite = background_subsection * (1 - alpha_mask) + foreground_colors * alpha_mask
# overwrite the section of the background image that has been updated
background[bg_y:bg_y + h, bg_x:bg_x + w] = composite
example usage:
background = cv2.imread('field.jpg')
overlay = cv2.imread('dice.png', cv2.IMREAD_UNCHANGED) # IMREAD_UNCHANGED => open image with the alpha channel
x_offset = 0
y_offset = 0
print("arrow keys to move the dice. ESC to quit")
while True:
img = background.copy()
add_transparent_image(img, overlay, x_offset, y_offset)
cv2.imshow("", img)
key = cv2.waitKey()
if key == 0: y_offset -= 10 # up
if key == 1: y_offset += 10 # down
if key == 2: x_offset -= 10 # left
if key == 3: x_offset += 10 # right
if key == 27: break # escape
You need to open the transparent png image using the flag IMREAD_UNCHANGED
Mat overlay = cv::imread("dice.png", IMREAD_UNCHANGED);
Then split the channels, group the RGB and use the transparent channel as an mask, do like that:
/**
* #brief Draws a transparent image over a frame Mat.
*
* #param frame the frame where the transparent image will be drawn
* #param transp the Mat image with transparency, read from a PNG image, with the IMREAD_UNCHANGED flag
* #param xPos x position of the frame image where the image will start.
* #param yPos y position of the frame image where the image will start.
*/
void drawTransparency(Mat frame, Mat transp, int xPos, int yPos) {
Mat mask;
vector<Mat> layers;
split(transp, layers); // seperate channels
Mat rgb[3] = { layers[0],layers[1],layers[2] };
mask = layers[3]; // png's alpha channel used as mask
merge(rgb, 3, transp); // put together the RGB channels, now transp insn't transparent
transp.copyTo(frame.rowRange(yPos, yPos + transp.rows).colRange(xPos, xPos + transp.cols), mask);
}
Can be called like that:
drawTransparency(background, overlay, 10, 10);
To overlay png image watermark over normal 3 channel jpeg image
import cv2
import numpy as np
def logoOverlay(image,logo,alpha=1.0,x=0, y=0, scale=1.0):
(h, w) = image.shape[:2]
image = np.dstack([image, np.ones((h, w), dtype="uint8") * 255])
overlay = cv2.resize(logo, None,fx=scale,fy=scale)
(wH, wW) = overlay.shape[:2]
output = image.copy()
# blend the two images together using transparent overlays
try:
if x<0 : x = w+x
if y<0 : y = h+y
if x+wW > w: wW = w-x
if y+wH > h: wH = h-y
print(x,y,wW,wH)
overlay=cv2.addWeighted(output[y:y+wH, x:x+wW],alpha,overlay[:wH,:wW],1.0,0)
output[y:y+wH, x:x+wW ] = overlay
except Exception as e:
print("Error: Logo position is overshooting image!")
print(e)
output= output[:,:,:3]
return output
Usage:
background = cv2.imread('image.jpeg')
overlay = cv2.imread('logo.png', cv2.IMREAD_UNCHANGED)
print(overlay.shape) # must be (x,y,4)
print(background.shape) # must be (x,y,3)
# downscale logo by half and position on bottom right reference
out = logoOverlay(background,overlay,scale=0.5,y=-100,x=-100)
cv2.imshow("test",out)
cv2.waitKey(0)
import cv2
import numpy as np
background = cv2.imread('background.jpg')
overlay = cv2.imread('cloudy.png')
overlay = cv2.resize(overlay, (200,200))
# overlay = for_transparent_removal(overlay)
h, w = overlay.shape[:2]
shapes = np.zeros_like(background, np.uint8)
shapes[0:h, 0:w] = overlay
alpha = 0.8
mask = shapes.astype(bool)
# option first
background[mask] = cv2.addWeighted(shapes, alpha, shapes, 1 - alpha, 0)[mask]
cv2.imwrite('combined.png', background)
# option second
background[mask] = cv2.addWeighted(background, alpha, overlay, 1 - alpha, 0)[mask]
# NOTE : above both option will give you image overlays but effect would be changed
cv2.imwrite('combined.1.png', background)
**Use this function to place your overlay on any background image.
if want to resize overlay use this overlay = cv2.resize(overlay, (200,200)) and then pass resized overlay into the function.
**
import cv2
import numpy as np
def image_overlay_second_method(img1, img2, location, min_thresh=0, is_transparent=False):
h, w = img1.shape[:2]
h1, w1 = img2.shape[:2]
x, y = location
roi = img1[y:y + h1, x:x + w1]
gray = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
_, mask = cv2.threshold(gray, min_thresh, 255, cv2.THRESH_BINARY)
mask_inv = cv2.bitwise_not(mask)
img_bg = cv2.bitwise_and(roi, roi, mask=mask_inv)
img_fg = cv2.bitwise_and(img2, img2, mask=mask)
dst = cv2.add(img_bg, img_fg)
if is_transparent:
dst = cv2.addWeighted(img1[y:y + h1, x:x + w1], 0.1, dst, 0.9, None)
img1[y:y + h1, x:x + w1] = dst
return img1
if __name__ == '__main__':
background = cv2.imread('background.jpg')
overlay = cv2.imread('overlay.png')
output = image_overlay_third_method(background, overlay, location=(800,50), min_thresh=0, is_transparent=True)
cv2.imwrite('output.png', output)
background.jpg
output.png
I am scanning old photos, so I have the image and a white background from the scanner. My aim is to take the picture, removing the white background. How can I do that ?
An example picture is the following:
My simple approach:
import os
import time
from PIL import Image
from collections import Counter
import numpy as np
def get_cropped_image(image, crop_folder, threshold):
image_name = image.split("\\")[-1]
im = Image.open(image)
pixels = im.load()
width, height = im.size
rows = []
for h_index in xrange(height):
row = []
for w_index in xrange(width):
row.append(pixels[((w_index, h_index))])
color_count = Counter(row)[(255, 255, 255)] / float(len(row))
rows.append([h_index, color_count])
columns = []
for w_index in xrange(width):
column = []
for h_index in xrange(height):
column.append(im.getpixel((w_index, h_index)))
color_count = Counter(column)[(255, 255, 255)] / float(len(column))
columns.append([w_index, color_count])
image_data = csv.writer(open("image_data.csv", "wb")).writerows(zip(rows, columns))
rows_indexes = [i[0] for i in rows if i[1] < threshold]
columns_indexes = [i[0] for i in columns if i[1] < threshold]
x1, y1, x2, y2 = columns_indexes[0], rows_indexes[0], columns_indexes[-1], rows_indexes[-1]
im.crop((x1, y1, x2, y2)).save(os.path.join(cropped_folder, "c_" + image_name))
In the example below, I create a mask by selecting all pixels that are close to white (close, because the values right outside the area of interest are not exactly white). I then invert the mask to find pixels potentially belonging to the image. I then calculate the bounding box of those pixels, and use it to extract the region of interest.
from skimage import io, img_as_float
import matplotlib.pyplot as plt
import numpy as np
image = img_as_float(io.imread('universe.jpg'))
# Select all pixels almost equal to white
# (almost, because there are some edge effects in jpegs
# so the boundaries may not be exactly white)
white = np.array([1, 1, 1])
mask = np.abs(image - white).sum(axis=2) < 0.05
# Find the bounding box of those pixels
coords = np.array(np.nonzero(~mask))
top_left = np.min(coords, axis=1)
bottom_right = np.max(coords, axis=1)
out = image[top_left[0]:bottom_right[0],
top_left[1]:bottom_right[1]]
plt.imshow(out)
plt.show()
How to cut off the blank border area of a PNG image and shrink it to its minimum size using Python?
NB: The border size is not a fixed value, but may vary per image.
PIL's getbbox is working for me
im.getbbox() => 4-tuple or None
Calculates the bounding box of the
non-zero regions in the image. The
bounding box is returned as a 4-tuple
defining the left, upper, right, and
lower pixel coordinate. If the image
is completely empty, this method
returns None.
Code Sample that I tried, I have tested with bmp, but it should work for png too.
import Image
im = Image.open("test.bmp")
im.size # (364, 471)
im.getbbox() # (64, 89, 278, 267)
im2 = im.crop(im.getbbox())
im2.size # (214, 178)
im2.save("test2.bmp")
Here is ready-to-use solution:
import numpy as np
from PIL import Image
def bbox(im):
a = np.array(im)[:,:,:3] # keep RGB only
m = np.any(a != [255, 255, 255], axis=2)
coords = np.argwhere(m)
y0, x0, y1, x1 = *np.min(coords, axis=0), *np.max(coords, axis=0)
return (x0, y0, x1+1, y1+1)
im = Image.open('test.png')
print(bbox(im)) # (33, 12, 223, 80)
im2 = im.crop(bbox(im))
im2.save('test_cropped.png')
Example input (download link if you want to try):
Output:
I had the same problem today. Here is my solution to crop the transparent borders. Just throw this script in your folder with your batch .png files:
from PIL import Image
import numpy as np
from os import listdir
def crop(png_image_name):
pil_image = Image.open(png_image_name)
np_array = np.array(pil_image)
blank_px = [255, 255, 255, 0]
mask = np_array != blank_px
coords = np.argwhere(mask)
x0, y0, z0 = coords.min(axis=0)
x1, y1, z1 = coords.max(axis=0) + 1
cropped_box = np_array[x0:x1, y0:y1, z0:z1]
pil_image = Image.fromarray(cropped_box, 'RGBA')
print(pil_image.width, pil_image.height)
pil_image.save(png_image_name)
print(png_image_name)
for f in listdir('.'):
if f.endswith('.png'):
crop(f)
https://gist.github.com/3141140
import Image
import sys
import glob
# Trim all png images with alpha in a folder
# Usage "python PNGAlphaTrim.py ../someFolder"
try:
folderName = sys.argv[1]
except :
print "Usage: python PNGPNGAlphaTrim.py ../someFolder"
sys.exit(1)
filePaths = glob.glob(folderName + "/*.png") #search for all png images in the folder
for filePath in filePaths:
image=Image.open(filePath)
image.load()
imageSize = image.size
imageBox = image.getbbox()
imageComponents = image.split()
if len(imageComponents) < 4: continue #don't process images without alpha
rgbImage = Image.new("RGB", imageSize, (0,0,0))
rgbImage.paste(image, mask=imageComponents[3])
croppedBox = rgbImage.getbbox()
if imageBox != croppedBox:
cropped=image.crop(croppedBox)
print filePath, "Size:", imageSize, "New Size:",croppedBox
cropped.save(filePath)
You can use PIL to find rows and cols of your image that are made up purely of your border color.
Using this information, you can easily determine the extents of the inlaid image.
PIL again will then allow you to crop the image to remove the border.
I think it's necessary to supplement #Frank Krueger's answer. He makes a good point, but it doesn't include how to properly crop extra border color out of an image. I found that here. Specifically, I found this useful:
from PIL import Image, ImageChops
def trim(im):
bg = Image.new(im.mode, im.size, im.getpixel((0,0)))
diff = ImageChops.difference(im, bg)
diff = ImageChops.add(diff, diff, 2.0, -100)
bbox = diff.getbbox()
if bbox:
return im.crop(bbox)
im = Image.open("bord3.jpg")
im = trim(im)
im.show()
The other answers did not work for me while writing a Blender script (cannot use PIL), so maybe someone else will find this useful.
import numpy as np
def crop(crop_file):
"""crop the image, removing invisible borders"""
image = bpy.data.images.load(crop_file, check_existing=False)
w, h = image.size
print("Original size: " + str(w) + " x " + str(h))
linear_pixels = image.pixels[:]
pixels4d = np.reshape(linear_pixels, (h, w, 4))
mask = pixels4d [:,:,3] != 0.
coords = np.argwhere(mask)
y0, x0 = coords.min(axis=0)
y1, x1 = coords.max(axis=0) + 1
cropped_box = pixels4d[y0:y1, x0:x1, :]
w1, h1 = x1 - x0, y1 - y0
print("Crop size: " + str(w1) + " x " + str(h1))
temp_image = bpy.data.images.new(crop_file, alpha=True, width=w1, height=h1)
temp_image.pixels[:] = cropped_box.ravel()
temp_image.filepath_raw = crop_file
temp_image.file_format = 'PNG'
temp_image.alpha_mode = 'STRAIGHT'
temp_image.save()