I need to cut this image into three parts using PIL and pick the middle part.
How do I do it?
http://thedilbertstore.com/images/periodic_content/dilbert/dt110507dhct.jpg
Say you have a really long picture like this.
And now you want to slice it up into smaller vertical bits, because it is so long.
Here is a Python script that will do that. This was useful to me for in preparing very long images for LaTeX docs.
from __future__ import division
import Image
import math
import os
def long_slice(image_path, out_name, outdir, slice_size):
"""slice an image into parts slice_size tall"""
img = Image.open(image_path)
width, height = img.size
upper = 0
left = 0
slices = int(math.ceil(height/slice_size))
count = 1
for slice in range(slices):
#if we are at the end, set the lower bound to be the bottom of the image
if count == slices:
lower = height
else:
lower = int(count * slice_size)
#set the bounding box! The important bit
bbox = (left, upper, width, lower)
working_slice = img.crop(bbox)
upper += slice_size
#save the slice
working_slice.save(os.path.join(outdir, "slice_" + out_name + "_" + str(count)+".png"))
count +=1
if __name__ == '__main__':
#slice_size is the max height of the slices in pixels
long_slice("longcat.jpg","longcat", os.getcwd(), 300)
This is is the output
I wanted to up-vote Gourneau's solution, but lack the sufficient reputation. However, I figured I would post the code that I developed as a result of his answer just in case it might be helpful to somebody else. I also added the ability to iterate through a file structure, and choose an image width.
import Image
import os
# Set the root directory
rootdir = 'path/to/your/file/directory'
def long_slice(image_path, out_name, outdir, sliceHeight, sliceWidth):
img = Image.open(image_path) # Load image
imageWidth, imageHeight = img.size # Get image dimensions
left = 0 # Set the left-most edge
upper = 0 # Set the top-most edge
while (left < imageWidth):
while (upper < imageHeight):
# If the bottom and right of the cropping box overruns the image.
if (upper + sliceHeight > imageHeight and \
left + sliceWidth > imageWidth):
bbox = (left, upper, imageWidth, imageHeight)
# If the right of the cropping box overruns the image
elif (left + sliceWidth > imageWidth):
bbox = (left, upper, imageWidth, upper + sliceHeight)
# If the bottom of the cropping box overruns the image
elif (upper + sliceHeight > imageHeight):
bbox = (left, upper, left + sliceWidth, imageHeight)
# If the entire cropping box is inside the image,
# proceed normally.
else:
bbox = (left, upper, left + sliceWidth, upper + sliceHeight)
working_slice = img.crop(bbox) # Crop image based on created bounds
# Save your new cropped image.
working_slice.save(os.path.join(outdir, 'slice_' + out_name + \
'_' + str(upper) + '_' + str(left) + '.jpg'))
upper += sliceHeight # Increment the horizontal position
left += sliceWidth # Increment the vertical position
upper = 0
if __name__ == '__main__':
# Iterate through all the files in a set of directories.
for subdir, dirs, files in os.walk(rootdir):
for file in files:
long_slice(subdir + '/' + file, 'longcat', subdir, 128, 128)
For this particular image you would do
import Image
i = Image.open('dt110507dhct.jpg')
frame2 = i.crop(((275, 0, 528, 250)))
frame2.save('dt110507dhct_frame2.jpg')
If the boxes are not known on before hand I would run a simple edge finding filter over the image (both x and y directions) to find the boundaries of the box.
A simple approach would be:
Run horizontal edge filter over image. You now have an image where each pixel describes the changes in intensity left and right of that pixel. I.e. it will "find" vertical lines.
For each column in the horizontal-edge-image get the average absolute magnitude of its rows. In the resulting 1 x WIDTH sized array you will find the vertical lines at the positions of highest value. Since the lines are more than one pixel wide yo might have to be a bit clever here.
Do the same for the other axis to find the horizontal lines.
You could do some pre processing by first extracting only pixels that are black (or near black) if you believe that the borders of the boxes will always be black. But I doubt it'd be necessary since the above method should be very stable.
Look at the crop() method of PIL
http://effbot.org/imagingbook/image.htm
(requires knowledge of the bounding box of the image...assuming that the image has the same dimensions every day you should be able to determine the bounding box once and use it for all the time).
Load the Image
Get the Size
Use the Crop method
Save the middle image
Related
I'm reading in an image with the Pillow library in Python. I want to "slice" it into squares, and save the corner coordinates of each of the squares in a list. For example in the image below, I would like to save the corner coordinates for square 15. (Top left corner is 0,0)
The first think I do after reading in the image is calculate the modulus of the height and width in pixels by the number of slices, and crop the image so the resulting number of pixels per square is the same and an integer.
from PIL import Image, ImageDraw, ImageFont
fileName = 'eyeImg_86.png'
img = Image.open(fileName)
vertical_slices = 8
horizontal_slices = 4
height = img.height
width = img.width
new_height = height - (height % horizontal_slices)
new_width = width - (width % vertical_slices)
img = img.crop((0, 0, new_width, new_height))
Then I calculate the size in pixels of each vertical and horizontal step.
horizontal_step = int(new_width / vertical_slices)
vertical_step = int(new_height / horizontal_slices)
And then I loop over the ranges between 0 to the total number of vertical and horizontal slices and append to a nested list (each inner list is a row)
points = []
for i in range(horizontal_slices+1):
row = []
for j in range(vertical_slices+1):
row.append((horizontal_step*j, vertical_step*i))
points.append(row)
Here's where I'm struggling to draw and to calculate what I need inside each of these squares. If I try to loop over all those points and draw them on the image.
with Image.open(fileName) as im:
im = im.convert(mode='RGB')
draw = ImageDraw.Draw(im)
for i in range(horizontal_slices+1):
if i < horizontal_slices:
for j in range(vertical_slices+1):
if j < vertical_slices:
draw.line([points[i][j], points[i+1][j-1]], fill=9999999)
Is there an easy way that I can dynamically give it the rows and columns and save each of the square coordinates to a list of tuples for example?
I'd like to both be able to draw them on top of the original image, and also calculate the number of black pixels inside each of the squares.
EDIT: To add some clarification, since the number of rows and columns of the grid is arbitrary, it will likely not be made of squares but rectangles. Furthermore, the numbering of these rectangles should be done row-wise from left to right, like reading.
Thank you
There were (from my understanding) inconsistencies in your use of "horizontal/vertical"; I also removed the points list, since you can easily convert the rectangle number to its upper-left corner coords (see the function in the end); I draw the grid directly by drawing all horizontal lines and all vertical lines).
from PIL import Image, ImageDraw, ImageFont
fileName = 'test.png'
img = Image.open(fileName)
vertical_slices = 8
horizontal_slices = 6
height = img.height
width = img.width
new_height = height - (height % vertical_slices)
new_width = width - (width % horizontal_slices)
img = img.crop((0, 0, new_width, new_height))
horizontal_step = int(new_width / horizontal_slices)
vertical_step = int(new_height / vertical_slices)
# drawing the grid
img = img.convert(mode='RGB')
pix = img.load()
draw = ImageDraw.Draw(img)
for i in range(horizontal_slices+1):
draw.line([(i*horizontal_step,0), (i*horizontal_step,new_height)], fill=9999999)
for j in range(vertical_slices+1):
draw.line([(0,j*vertical_step), (new_width,j*vertical_step)], fill=9999999)
# with rectangles being numbered from 1 (upper left) to v_slices*h_slices (lower right) in reading order
def num_to_ul_corner_coords(num):
i = (num-1)%horizontal_slices
j = (num-1)//horizontal_slices
return(i*horizontal_step,j*vertical_step)
This should do what you want, provided your picture is pure black and white:
def count_black_pixels(num) :
cnt = 0
x, y = num_to_ul_corner_coords(num)
for i in range(horizontal_step):
for j in range(vertical_step):
if pix[x+i,y+j] == (0,0,0):
cnt += 1
perc = round(cnt/(horizontal_step*vertical_step)*100,2)
return cnt, perc
I want to perform image translation by a certain amount (shift the image vertically and horizontally).
The problem is that when I paste the cropped image back on the canvas, I just get back a white blank box.
Can anyone spot the issue here?
Many thanks
img_shape = image.shape
# translate image
# percentage of the dimension of the image to translate
translate_factor_x = random.uniform(*translate)
translate_factor_y = random.uniform(*translate)
# initialize a black image the same size as the image
canvas = np.zeros(img_shape)
# get the top-left corner coordinates of the shifted image
corner_x = int(translate_factor_x*img_shape[1])
corner_y = int(translate_factor_y*img_shape[0])
# determine which part of the image will be pasted
mask = image[max(-corner_y, 0):min(img_shape[0], -corner_y + img_shape[0]),
max(-corner_x, 0):min(img_shape[1], -corner_x + img_shape[1]),
:]
# determine which part of the canvas the image will be pasted on
target_coords = [max(0,corner_y),
max(corner_x,0),
min(img_shape[0], corner_y + img_shape[0]),
min(img_shape[1],corner_x + img_shape[1])]
# paste image on selected part of the canvas
canvas[target_coords[0]:target_coords[2], target_coords[1]:target_coords[3],:] = mask
transformed_img = canvas
plt.imshow(transformed_img)
This is what I get:
For image translation, you can make use of the somewhat obscure numpy.roll function. In this example I'm going to use a white canvas so it is easier to visualize.
image = np.full_like(original_image, 255)
height, width = image.shape[:-1]
shift = 100
# shift image
rolled = np.roll(image, shift, axis=[0, 1])
# black out shifted parts
rolled = cv2.rectangle(rolled, (0, 0), (width, shift), 0, -1)
rolled = cv2.rectangle(rolled, (0, 0), (shift, height), 0, -1)
If you want to flip the image so the black part is on the other side, you can use both np.fliplr and np.flipud.
Result:
Here is a simple solution that translates an image by tx and ty pixels using only array indexing, that does not roll over, and handles negative values as well:
tx, ty = 8, 5 # translation on x and y axis, in pixels
N, M = image.shape
image_translated = np.zeros_like(image)
image_translated[max(tx,0):M+min(tx,0), max(ty,0):N+min(ty,0)] = image[-min(tx,0):M-max(tx,0), -min(ty,0):N-max(ty,0)]
Example:
(Note that for simplicity it does not handle cases where tx > M or ty > N).
I have binary images where rectangles are placed randomly and I want to get the positions and sizes of those rectangles.
If possible I want the minimal number of rectangles necessary to exactly recreate the image.
On the left is my original image and on the right the image I get after applying scipys.find_objects()
(like suggested for this question).
import scipy
# image = scipy.ndimage.zoom(image, 9, order=0)
labels, n = scipy.ndimage.measurements.label(image, np.ones((3, 3)))
bboxes = scipy.ndimage.measurements.find_objects(labels)
img_new = np.zeros_like(image)
for bb in bboxes:
img_new[bb[0], bb[1]] = 1
This works fine if the rectangles are far apart, but if they overlap and build more complex structures this algorithm just gives me the largest bounding box (upsampling the image made no difference). I have the feeling that there should already exist a scipy or opencv method which does this.
I would be glad to know if somebody has an idea on how to tackle this problem or even better knows of an existing solution.
As result I want a list of rectangles (ie. lower-left-corner : upper-righ-corner) in the image. The condition is that when I redraw those filled rectangles I want to get exactly the same image as before. If possible the number of rectangles should be minimal.
Here is the code for generating sample images (and a more complex example original vs scipy)
import numpy as np
def random_rectangle_image(grid_size, n_obstacles, rectangle_limits):
n_dim = 2
rect_pos = np.random.randint(low=0, high=grid_size-rectangle_limits[0]+1,
size=(n_obstacles, n_dim))
rect_size = np.random.randint(low=rectangle_limits[0],
high=rectangle_limits[1]+1,
size=(n_obstacles, n_dim))
# Crop rectangle size if it goes over the boundaries of the world
diff = rect_pos + rect_size
ex = np.where(diff > grid_size, True, False)
rect_size[ex] -= (diff - grid_size)[ex].astype(int)
img = np.zeros((grid_size,)*n_dim, dtype=bool)
for i in range(n_obstacles):
p_i = np.array(rect_pos[i])
ps_i = p_i + np.array(rect_size[i])
img[tuple(map(slice, p_i, ps_i))] = True
return img
img = random_rectangle_image(grid_size=64, n_obstacles=30,
rectangle_limits=[4, 10])
Here is something to get you started: a naïve algorithm that walks your image and creates rectangles as large as possible. As it is now, it only marks the rectangles but does not report back coordinates or counts. This is to visualize the algorithm alone.
It does not need any external libraries except for PIL, to load and access the left side image when saved as a PNG. I'm assuming a border of 15 pixels all around can be ignored.
from PIL import Image
def fill_rect (pixels,xp,yp,w,h):
for y in range(h):
for x in range(w):
pixels[xp+x,yp+y] = (255,0,0,255)
for y in range(h):
pixels[xp,yp+y] = (255,192,0,255)
pixels[xp+w-1,yp+y] = (255,192,0,255)
for x in range(w):
pixels[xp+x,yp] = (255,192,0,255)
pixels[xp+x,yp+h-1] = (255,192,0,255)
def find_rect (pixels,x,y,maxx,maxy):
# assume we're at the top left
# get max horizontal span
width = 0
height = 1
while x+width < maxx and pixels[x+width,y] == (0,0,0,255):
width += 1
# now walk down, adjusting max width
while y+height < maxy:
for w in range(x,x+width,1):
if pixels[x,y+height] != (0,0,0,255):
break
if pixels[x,y+height] != (0,0,0,255):
break
height += 1
# fill rectangle
fill_rect (pixels,x,y,width,height)
image = Image.open('A.png')
pixels = image.load()
width, height = image.size
print (width,height)
for y in range(16,height-15,1):
for x in range(16,width-15,1):
if pixels[x,y] == (0,0,0,255):
find_rect (pixels,x,y,width,height)
image.show()
From the output
you can observe the detection algorithm can be improved, as, for example, the "obvious" two top left rectangles are split up into 3. Similar, the larger structure in the center also contains one rectangle more than absolutely needed.
Possible improvements are either to adjust the find_rect routine to locate a best fit¹, or store the coordinates and use math (beyond my ken) to find which rectangles may be joined.
¹ A further idea on this. Currently all found rectangles are immediately filled with the "found" color. You could try to detect obviously multiple rectangles, and then, after marking the first, the other rectangle(s) to check may then either be black or red. Off the cuff I'd say you'd need to try different scan orders (top-to-bottom or reverse, left-to-right or reverse) to actually find the minimally needed number of rectangles in any combination.
I have a set of arbitrary images. Half the images are pictures, half are masks defining ROIS.
In the current version of my program I use the ROI to crop the image (i.e I extract the rectangle in the image matching the bounding box of the ROI mask). The problem is, the ROI mask isn't perfect and it's better to over predict than under predict in my case.
So I want to copy more than the ROI rectangle, but if I do this, I may be trying to crop out of the image.
i.e:
x, y, w, h = cv2.boundingRect(mask_contour)
img = img[int(y-h*0.05):int(y + h * 1.05), int(x-w*0.05):int(x + w * 1.05)]
can fail because it tries to access out of bounds pixels. I could just clamp the values, but I wanted to know if there is a better approach
You can add a boarder using OpenCV
import cv2 as cv
import random
src = cv.imread('/home/stephen/lenna.png')
borderType = cv.BORDER_REPLICATE
boarderSize = .5
top = int(boarderSize * src.shape[0]) # shape[0] = rows
bottom = top
left = int(boarderSize * src.shape[1]) # shape[1] = cols
right = left
value = [random.randint(0,255), random.randint(0,255), random.randint(0,255)]
dst = cv.copyMakeBorder(src, top, bottom, left, right, borderType, None, value)
cv.imshow('img', dst)
c = cv.waitKey(0)
Maybe you could try to limit the coordinates beforehand. Please see the code below:
[ymin, ymax] = [max(0,int(y-h*0.05)), min(h, int(y+h*1.05))]
[xmin, xmax] = [max(0,int(x-w*1.05)), min(w, int(x+w*1.05))]
img = img[ymin:ymax, xmin:xmax]
I am probably looking for the wrong thing in the handbook, but I am looking to take an image object and expand it without resizing (stretching/squishing) the original image.
Toy example: imagine a blue rectangle, 200 x 100, then I perform some operation and I have a new image object, 400 x 300, consisting of a white background upon which a 200 x 100 blue rectangle rests. Bonus if I can control in which direction this expands, or the new background color, etc.
Essentially, I have an image to which I will be adding iteratively, and I do not know what size it will be at the outset.
I suppose it would be possible for me to grab the original object, make a new, slightly larger object, paste the original on there, draw a little more, then repeat. It seems like it might be computationally expensive. However, I thought there would be a function for this, as I assume it is a common operation. Perhaps I assumed wrong.
The ImageOps.expand function will expand the image, but it adds the same amount of pixels in each direction.
The best way is simply to make a new image and paste:
newImage = Image.new(mode, (newWidth,newHeight))
newImage.paste(srcImage, (x1,y1,x1+oldWidth,y1+oldHeight))
If performance is an issue, make your original image bigger than needed and crop it after the drawing is done.
Based on interjays answer:
#!/usr/bin/env python
from PIL import Image
import math
def resize_canvas(old_image_path="314.jpg", new_image_path="save.jpg",
canvas_width=500, canvas_height=500):
"""
Resize the canvas of old_image_path.
Store the new image in new_image_path. Center the image on the new canvas.
Parameters
----------
old_image_path : str
new_image_path : str
canvas_width : int
canvas_height : int
"""
im = Image.open(old_image_path)
old_width, old_height = im.size
# Center the image
x1 = int(math.floor((canvas_width - old_width) / 2))
y1 = int(math.floor((canvas_height - old_height) / 2))
mode = im.mode
if len(mode) == 1: # L, 1
new_background = (255)
if len(mode) == 3: # RGB
new_background = (255, 255, 255)
if len(mode) == 4: # RGBA, CMYK
new_background = (255, 255, 255, 255)
newImage = Image.new(mode, (canvas_width, canvas_height), new_background)
newImage.paste(im, (x1, y1, x1 + old_width, y1 + old_height))
newImage.save(new_image_path)
resize_canvas()
You might consider a rather different approach to your image... build it out of tiles of a fixed size. That way, as you need to expand, you just add new image tiles. When you have completed all of your computation, you can determine the final size of the image, create a blank image of that size, and paste the tiles into it. That should reduce the amount of copying you're looking at for completing the task.
(You'd likely want to encapsulate such a tiled image into an object that hid the tiling aspects from the other layers of code, of course.)
This code will enlarge a smaller image, preserving aspect ratio, then center it on a standard sized canvas. Also preserves transparency, or defaults to gray background.
Tested with P mode PNG files.
Coded debug final.show() and break for testing. Remove lines and hashtag on final.save(...) to loop and save.
Could parameterize canvas ratio and improve flexibility, but it served my purpose.
"""
Resize ... and reconfigures. images in a specified directory
Use case: Images of varying size, need to be enlarged to exaxtly 1200 x 1200
"""
import os
import glob
from PIL import Image
# Source directory plus Glob file reference (Windows)
source_path = os.path.join('C:', os.sep, 'path', 'to', 'source', '*.png')
# List of UNC Image File paths
images = glob.glob(source_path)
# Destination directory of modified image (Windows)
destination_path = os.path.join('C:', os.sep, 'path', 'to', 'destination')
for image in images:
original = Image.open(image)
# Retain original attributes (ancillary chunks)
info = original.info
# Retain original mode
mode = original.mode
# Retain original palette
if original.palette is not None:
palette = original.palette.getdata()[1]
else:
palette = False
# Match original aspect ratio
dimensions = original.getbbox()
# Identify destination image background color
if 'transparency' in info.keys():
background = original.info['transparency']
else:
# Image does not have transparency set
print(image)
background = (64)
# Get base filename and extension for destination
filename, extension = os.path.basename(image).split('.')
# Calculate matched aspect ratio
if dimensions[2] > dimensions[3]:
width = int(1200)
modifier = width / dimensions[2]
length = int(dimensions[3] * modifier)
elif dimensions[3] > dimensions[2]:
length = int(1200)
modifier = length / dimensions[3]
width = int(dimensions[2] * modifier)
else:
width, length = (1200, 1200)
size = (width, length)
# Set desired final image size
canvas = (1200, 1200)
# Calculate center position
position = (
int((1200 - width)/2),
int((1200 - length)/2),
int((1200 - width)/2) + width,
int((1200 - length)/2) + length
)
# Enlarge original image proportionally
resized = original.resize(size, Image.LANCZOS)
# Then create sized canvas
final = Image.new(mode, canvas, background)
# Replicate original properties
final.info = info
# Replicate original palatte
if palette:
final.putpalette(palette)
# Cemter paste resized image to final canvas
final.paste(resized, position)
# Save final image to destination directory
final.show()
#final.save("{}\\{}.{}".format(destination_path, filename, extension))
break