Here I use the PIL Library to read and manipulate images. I am confused, how to create a new image from the list of arrays containing binary pixel data, after being converted to binary images.
I have tried it, but the resulting image is of type RGB, not a binary image. The following is the code that I wrote:
from PIL import Image
import numpy as np
img = Image.open('data_train/ga.jpeg')
pixels = img.load()
width, height = img.size
all_pixels = []
for x in range(width):
for y in range(height):
hpixel = pixels[x, y]
img_gray = (0.2989 * hpixel[0]) + (0.5870 * hpixel[1]) + (0.1140 * hpixel[2])
if img_gray >= 110:
all_pixels.append('1')
else:
all_pixels.append('0')
data_isi = {'0': 0,
'1': 255}
data = [data_isi[letter] for letter in all_pixels]
img_new = Image.fromarray(data)
img_new.save('data_train/gabiner.jpeg')
Updated Answer
As you are required to use a for loop, you could go with something more like this:
#!/usr/bin/env python3
from PIL import Image
# Load image and get dimensions
img = Image.open('start.jpg').convert('RGB')
width, height = img.size
# Actually load input pixels, else PIL is too lazy
imi = img.load()
# List of result pixels
imo = []
for y in range(height):
for x in range(width):
R, G, B = imi[x, y]
gray = (0.2989 * R) + (0.5870 * G) + (0.1140 * B)
if gray >= 110:
imo.append(255)
else:
imo.append(0)
# Make output image and put output pixels into it
result = Image.new('L', (width,height))
result.putdata(imo)
# Save result
result.save('result.png')
Which turns this start image:
Into this result:
Original Answer
You appear to be converting the image to greyscale and thresholding at 110, which can be done much more simply, and faster, like this:
#!/usr/local/bin/python3
from PIL import Image
# Load image and make greyscale
im = Image.open('image.png').convert('L')
# Threshold to make black and white
thr = im.point(lambda p: p > 110 and 255)
# Save result
thr.save('result.png')
As from ESA snap, for a RGB image we should put Band 4 into Red Channel, Band 3 into Green Channel and Band 2 into Blue Channel. How can we read those bands with python into a numpy array so we could do whatever image processing we want and then save a RGB image on disk?
from snappy import Product
from snappy import ProductIO
import numpy as np
import cv2
product = ProductIO.readProduct(path_to_product)
width = product.getSceneRasterWidth()
height = product.getSceneRasterHeight()
# Natural colors
red = product.getBand('B4')
green = product.getBand('B3')
blue = product.getBand('B2')
For example here is the type of one of the above variables (same for the others):
type(red)
# org.esa.snap.core.datamodel.Band
How can I get numpy arrays from these data, and subsequently save them to disk as jpg images?
#Read in channel's pixels
red_pixels = np.zeros(width * height, np.float32)
red.readPixels(0, 0, width, height, red_pixels)
green_pixels = np.zeros(width * height, np.float32)
green.readPixels(0, 0, width, height, green_pixels)
blue_pixels = np.zeros(width * height, np.float32)
blue.readPixels(0, 0, width, height, blue_pixels)
#Reshape to image dimensions
red_pixels.shape = height, width
green_pixels.shape = height, width
blue_pixels.shape = height, width
#Combine into a RGB image
rgb=np.zeros((height,width,3))
rgb[...,0] = red_pixels
rgb[...,1] = green_pixels
rgb[...,2] = blue_pixels
So far we have a rgb image in a numpy array with float values. In order to write to disk as a jpg image, we first clip large values to make image brighter, and then convert the image to 0-255 integer values.
rgb2 = ((np.clip(rgb.copy(),0,1))*255).astype('uint8')
#Reverse Red-Blue Channels as open cv will reverse again upon writing image on disk
cv2.imwrite('image_name.jpg',rgb2[...,::-1])
Like the image above suggests, how can I convert the image to the left into an array that represent the darkness of the image between 0 for white and decimals for darker colours closer to 1? as shown in the image usingpython 3`?
Update:
I have tried to work abit more on this. There are good answers below too.
# Load image
filename = tf.constant("one.png")
image_file = tf.read_file(filename)
# Show Image
Image("one.png")
#convert method
def convertRgbToWeight(rgbArray):
arrayWithPixelWeight = []
for i in range(int(rgbArray.size / rgbArray[0].size)):
for j in range(int(rgbArray[0].size / 3)):
lum = 255-((rgbArray[i][j][0]+rgbArray[i][j][1]+rgbArray[i][j][2])/3) # Reversed luminosity
arrayWithPixelWeight.append(lum/255) # Map values from range 0-255 to 0-1
return arrayWithPixelWeight
# Convert image to numbers and print them
image_decoded_png = tf.image.decode_png(image_file,channels=3)
image_as_float32 = tf.cast(image_decoded_png, tf.float32)
numpy.set_printoptions(threshold=numpy.nan)
sess = tf.Session()
squeezedArray = sess.run(image_as_float32)
convertedList = convertRgbToWeight(squeezedArray)
print(convertedList) # This will give me an array of numbers.
I would recommend to read in images with opencv. The biggest advantage of opencv is that it supports multiple image formats and it automatically transforms the image into a numpy array. For example:
import cv2
import numpy as np
img_path = '/YOUR/PATH/IMAGE.png'
img = cv2.imread(img_path, 0) # read image as grayscale. Set second parameter to 1 if rgb is required
Now img is a numpy array with values between 0 - 255. By default 0 equals black and 255 equals white. To change this you can use the opencv built in function bitwise_not:
img_reverted= cv2.bitwise_not(img)
We can now scale the array with:
new_img = img_reverted / 255.0 // now all values are ranging from 0 to 1, where white equlas 0.0 and black equals 1.0
Load the image and then just invert and divide by 255.
Here is the image ('Untitled.png') that I used for this example: https://ufile.io/h8ncw
import numpy as np
import cv2
import matplotlib.pyplot as plt
my_img = cv2.imread('Untitled.png')
inverted_img = (255.0 - my_img)
final = inverted_img / 255.0
# Visualize the result
plt.imshow(final)
plt.show()
print(final.shape)
(661, 667, 3)
Results (final object represented as image):
You can use PIL package to manage images. Here's example how it can be done.
from PIL import Image
image = Image.open('sample.png')
width, height = image.size
pixels = image.load()
# Check if has alpha, to avoid "too many values to unpack" error
has_alpha = len(pixels[0,0]) == 4
# Create empty 2D list
fill = 1
array = [[fill for x in range(width)] for y in range(height)]
for y in range(height):
for x in range(width):
if has_alpha:
r, g, b, a = pixels[x,y]
else:
r, g, b = pixels[x,y]
lum = 255-((r+g+b)/3) # Reversed luminosity
array[y][x] = lum/255 # Map values from range 0-255 to 0-1
I think it works but please note that the only test I did was if values are in desired range:
# Test max and min values
h, l = 0,1
for row in array:
h = max([max(row), h])
l = min([min(row), l])
print(h, l)
You have to load the image from the path and then transform it to a numpy array.
The values of the image will be between 0 and 255. The next step is to standardize the numpy array.
Hope it helps.
I'm using PIL to convert a transparent PNG image uploaded with Django to a JPG file. The output looks broken.
Source file
Code
Image.open(object.logo.path).save('/tmp/output.jpg', 'JPEG')
or
Image.open(object.logo.path).convert('RGB').save('/tmp/output.png')
Result
Both ways, the resulting image looks like this:
Is there a way to fix this? I'd like to have white background where the transparent background used to be.
Solution
Thanks to the great answers, I've come up with the following function collection:
import Image
import numpy as np
def alpha_to_color(image, color=(255, 255, 255)):
"""Set all fully transparent pixels of an RGBA image to the specified color.
This is a very simple solution that might leave over some ugly edges, due
to semi-transparent areas. You should use alpha_composite_with color instead.
Source: http://stackoverflow.com/a/9166671/284318
Keyword Arguments:
image -- PIL RGBA Image object
color -- Tuple r, g, b (default 255, 255, 255)
"""
x = np.array(image)
r, g, b, a = np.rollaxis(x, axis=-1)
r[a == 0] = color[0]
g[a == 0] = color[1]
b[a == 0] = color[2]
x = np.dstack([r, g, b, a])
return Image.fromarray(x, 'RGBA')
def alpha_composite(front, back):
"""Alpha composite two RGBA images.
Source: http://stackoverflow.com/a/9166671/284318
Keyword Arguments:
front -- PIL RGBA Image object
back -- PIL RGBA Image object
"""
front = np.asarray(front)
back = np.asarray(back)
result = np.empty(front.shape, dtype='float')
alpha = np.index_exp[:, :, 3:]
rgb = np.index_exp[:, :, :3]
falpha = front[alpha] / 255.0
balpha = back[alpha] / 255.0
result[alpha] = falpha + balpha * (1 - falpha)
old_setting = np.seterr(invalid='ignore')
result[rgb] = (front[rgb] * falpha + back[rgb] * balpha * (1 - falpha)) / result[alpha]
np.seterr(**old_setting)
result[alpha] *= 255
np.clip(result, 0, 255)
# astype('uint8') maps np.nan and np.inf to 0
result = result.astype('uint8')
result = Image.fromarray(result, 'RGBA')
return result
def alpha_composite_with_color(image, color=(255, 255, 255)):
"""Alpha composite an RGBA image with a single color image of the
specified color and the same size as the original image.
Keyword Arguments:
image -- PIL RGBA Image object
color -- Tuple r, g, b (default 255, 255, 255)
"""
back = Image.new('RGBA', size=image.size, color=color + (255,))
return alpha_composite(image, back)
def pure_pil_alpha_to_color_v1(image, color=(255, 255, 255)):
"""Alpha composite an RGBA Image with a specified color.
NOTE: This version is much slower than the
alpha_composite_with_color solution. Use it only if
numpy is not available.
Source: http://stackoverflow.com/a/9168169/284318
Keyword Arguments:
image -- PIL RGBA Image object
color -- Tuple r, g, b (default 255, 255, 255)
"""
def blend_value(back, front, a):
return (front * a + back * (255 - a)) / 255
def blend_rgba(back, front):
result = [blend_value(back[i], front[i], front[3]) for i in (0, 1, 2)]
return tuple(result + [255])
im = image.copy() # don't edit the reference directly
p = im.load() # load pixel array
for y in range(im.size[1]):
for x in range(im.size[0]):
p[x, y] = blend_rgba(color + (255,), p[x, y])
return im
def pure_pil_alpha_to_color_v2(image, color=(255, 255, 255)):
"""Alpha composite an RGBA Image with a specified color.
Simpler, faster version than the solutions above.
Source: http://stackoverflow.com/a/9459208/284318
Keyword Arguments:
image -- PIL RGBA Image object
color -- Tuple r, g, b (default 255, 255, 255)
"""
image.load() # needed for split()
background = Image.new('RGB', image.size, color)
background.paste(image, mask=image.split()[3]) # 3 is the alpha channel
return background
Performance
The simple non-compositing alpha_to_color function is the fastest solution, but leaves behind ugly borders because it does not handle semi transparent areas.
Both the pure PIL and the numpy compositing solutions give great results, but alpha_composite_with_color is much faster (8.93 msec) than pure_pil_alpha_to_color (79.6 msec). If numpy is available on your system, that's the way to go. (Update: The new pure PIL version is the fastest of all mentioned solutions.)
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_to_color(i)"
10 loops, best of 3: 4.67 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.alpha_composite_with_color(i)"
10 loops, best of 3: 8.93 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color(i)"
10 loops, best of 3: 79.6 msec per loop
$ python -m timeit "import Image; from apps.front import utils; i = Image.open(u'logo.png'); i2 = utils.pure_pil_alpha_to_color_v2(i)"
10 loops, best of 3: 1.1 msec per loop
Here's a version that's much simpler - not sure how performant it is. Heavily based on some django snippet I found while building RGBA -> JPG + BG support for sorl thumbnails.
from PIL import Image
png = Image.open(object.logo.path)
png.load() # required for png.split()
background = Image.new("RGB", png.size, (255, 255, 255))
background.paste(png, mask=png.split()[3]) # 3 is the alpha channel
background.save('foo.jpg', 'JPEG', quality=80)
Result #80%
Result # 50%
By using Image.alpha_composite, the solution by Yuji 'Tomita' Tomita become simpler. This code can avoid a tuple index out of range error if png has no alpha channel.
from PIL import Image
png = Image.open(img_path).convert('RGBA')
background = Image.new('RGBA', png.size, (255, 255, 255))
alpha_composite = Image.alpha_composite(background, png)
alpha_composite.save('foo.jpg', 'JPEG', quality=80)
The transparent parts mostly have RGBA value (0,0,0,0). Since the JPG has no transparency, the jpeg value is set to (0,0,0), which is black.
Around the circular icon, there are pixels with nonzero RGB values where A = 0. So they look transparent in the PNG, but funny-colored in the JPG.
You can set all pixels where A == 0 to have R = G = B = 255 using numpy like this:
import Image
import numpy as np
FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
x = np.array(img)
r, g, b, a = np.rollaxis(x, axis = -1)
r[a == 0] = 255
g[a == 0] = 255
b[a == 0] = 255
x = np.dstack([r, g, b, a])
img = Image.fromarray(x, 'RGBA')
img.save('/tmp/out.jpg')
Note that the logo also has some semi-transparent pixels used to smooth the edges around the words and icon. Saving to jpeg ignores the semi-transparency, making the resultant jpeg look quite jagged.
A better quality result could be made using imagemagick's convert command:
convert logo.png -background white -flatten /tmp/out.jpg
To make a nicer quality blend using numpy, you could use alpha compositing:
import Image
import numpy as np
def alpha_composite(src, dst):
'''
Return the alpha composite of src and dst.
Parameters:
src -- PIL RGBA Image object
dst -- PIL RGBA Image object
The algorithm comes from http://en.wikipedia.org/wiki/Alpha_compositing
'''
# http://stackoverflow.com/a/3375291/190597
# http://stackoverflow.com/a/9166671/190597
src = np.asarray(src)
dst = np.asarray(dst)
out = np.empty(src.shape, dtype = 'float')
alpha = np.index_exp[:, :, 3:]
rgb = np.index_exp[:, :, :3]
src_a = src[alpha]/255.0
dst_a = dst[alpha]/255.0
out[alpha] = src_a+dst_a*(1-src_a)
old_setting = np.seterr(invalid = 'ignore')
out[rgb] = (src[rgb]*src_a + dst[rgb]*dst_a*(1-src_a))/out[alpha]
np.seterr(**old_setting)
out[alpha] *= 255
np.clip(out,0,255)
# astype('uint8') maps np.nan (and np.inf) to 0
out = out.astype('uint8')
out = Image.fromarray(out, 'RGBA')
return out
FNAME = 'logo.png'
img = Image.open(FNAME).convert('RGBA')
white = Image.new('RGBA', size = img.size, color = (255, 255, 255, 255))
img = alpha_composite(img, white)
img.save('/tmp/out.jpg')
Here's a solution in pure PIL.
def blend_value(under, over, a):
return (over*a + under*(255-a)) / 255
def blend_rgba(under, over):
return tuple([blend_value(under[i], over[i], over[3]) for i in (0,1,2)] + [255])
white = (255, 255, 255, 255)
im = Image.open(object.logo.path)
p = im.load()
for y in range(im.size[1]):
for x in range(im.size[0]):
p[x,y] = blend_rgba(white, p[x,y])
im.save('/tmp/output.png')
It's not broken. It's doing exactly what you told it to; those pixels are black with full transparency. You will need to iterate across all pixels and convert ones with full transparency to white.
import numpy as np
import PIL
def convert_image(image_file):
image = Image.open(image_file) # this could be a 4D array PNG (RGBA)
original_width, original_height = image.size
np_image = np.array(image)
new_image = np.zeros((np_image.shape[0], np_image.shape[1], 3))
# create 3D array
for each_channel in range(3):
new_image[:,:,each_channel] = np_image[:,:,each_channel]
# only copy first 3 channels.
# flushing
np_image = []
return new_image
from PIL import Image
def fig2img ( fig ):
"""
#brief Convert a Matplotlib figure to a PIL Image in RGBA format and return it
#param fig a matplotlib figure
#return a Python Imaging Library ( PIL ) image
"""
# put the figure pixmap into a numpy array
buf = fig2data ( fig )
w, h, d = buf.shape
return Image.frombytes( "RGBA", ( w ,h ), buf.tostring( ) )
def fig2data ( fig ):
"""
#brief Convert a Matplotlib figure to a 4D numpy array with RGBA channels and return it
#param fig a matplotlib figure
#return a numpy 3D array of RGBA values
"""
# draw the renderer
fig.canvas.draw ( )
# Get the RGBA buffer from the figure
w,h = fig.canvas.get_width_height()
buf = np.fromstring ( fig.canvas.tostring_argb(), dtype=np.uint8 )
buf.shape = ( w, h, 4 )
# canvas.tostring_argb give pixmap in ARGB mode. Roll the ALPHA channel to have it in RGBA mode
buf = np.roll ( buf, 3, axis = 2 )
return buf
def rgba2rgb(img, c=(0, 0, 0), path='foo.jpg', is_already_saved=False, if_load=True):
if not is_already_saved:
background = Image.new("RGB", img.size, c)
background.paste(img, mask=img.split()[3]) # 3 is the alpha channel
background.save(path, 'JPEG', quality=100)
is_already_saved = True
if if_load:
if is_already_saved:
im = Image.open(path)
return np.array(im)
else:
raise ValueError('No image to load.')