Why is my code only working on part of my image? - python

I created code to equalize the luminosity values of pixels in an image so that when the image is further edited I do not have dark or light spots in my final image. However, the code seems to stop short and only equalize part of my image. Any ideas as to why the code is stopping early?
Here is my code:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
img = mpimg.imread('EXP_0159-2_8b.tif')
imgOut = img.copy()
for i in range(0, len(img[0, :])):
imgLine1 = (img[:, i] < 165) * img[:, i]
p = imgLine1.nonzero()
if len(p[0]) < 1:
imgOut[:, i] == 0
else:
imgLine2 = imgLine1[p[0]]
def curvefitting(lineFunction):
x = np.arange(0, len(lineFunction))
y = lineFunction
curve = np.polyfit(x, y, deg = 2)
a = curve[0]
b = curve[1]
c = curve[2]
curveEquation = (a*(x**2)) + (b*(x**1)) + (c)
curveCorrected = lineFunction - curveEquation + 200
return curveCorrected
imgLine1[p[0]] = curvefitting(imgLine2)
imgOut[:, i] = imgLine1
plt.imshow(imgOut, cmap = 'gray')
The for loop takes the individual columns of pixels in my image and restricts the endpoints of that column to (0, 165), so that pixels outside of that range are turned into zero and ignored by the nonzero() function. The if condition just finalizes the conversion of values outside (0, 165) to zero. Additionally, I converted the image to gray so I would not have to deal with colors and could focus only on luminosity.
This is my corrected image. The program works to average the luminosity values across the entire surface. However, you can see that it stops before reaching the end. The initial image was darker on the sides and lighter in the middle, but the file is too large to upload.
Any help is greatly appreciated.

If you are not interested in color you can convert input image to grayscale. That would simplified the matrix multiplications. The simplified version would be
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
def rgb2gray(rgb):
return np.dot(rgb[...,:3], [0.2989, 0.5870, 0.1140])
def curvefitting(lineFunction):
x = np.arange(0, len(lineFunction))
y = lineFunction
curve = np.polyfit(x, y, deg = 2)
a = curve[0]
b = curve[1]
c = curve[2]
curveEquation = [(a*(x_**2)) + (b*(x_**1)) + (c) for x_ in x]
curveCorrected = lineFunction - curveEquation + 200
return curveCorrected
img = mpimg.imread('EXP_0159-2_8b.tif')
img = rgb2gray(img)
imgOut = img.copy()
for i in range(0, len(img[0, :])):
imgLine1 = (img[:, i] < 165) * img[:, i]
p = imgLine1.nonzero()
if len(p) < 1:
imgOut[:, i] == 0
else:
imgLine2 = imgLine1[p]
imgLine1[p] = curvefitting(imgLine2)
imgOut[:, i] = imgLine1
plt.imshow(imgOut, cmap = 'gray')
plt.show()

Related

Create 2d image from point cloud

I am trying to project a point cloud into a 2d image as if it were a satellite image.
I have six files I want to project and the point clouds are quite big.
For the biggest one, I have len(las.X) = 37_763_608, max(las.X) - min(las.X) = 122_124, and max(las.X) - min(las.X) = 273_683, so sometimes when calculate the size I have an overflow error.
My first try was this, but this was quite slow and took about 28 minutes to run.
Here I added the loops with k_x and k_y because the image I got was mostly black, and I wanted to have colour everywhere. I tried looping around each point/pixel to make them 5 times bigger, but this is the slow part.
see pictures
Colour version with the k padding
Black and white version without the padding
Ideally, I would like to have the colour from one point/pixel shift to the colour of their neighbours, so that there is a gradient between them, and no have any black leftover from me initialize the image as np.zeros
import laspy
import numpy as np
from PIL import Image
import cv2
from tqdm import tqdm
las = laspy.read("area1.las")
def las_to_rgb(las):
x, y = las.X, las.Y
delta_x = max(x) - min(x)
delta_y = max(y) - min(y)
re_x = x - min(x)
re_y = y - min(y)
# las.red, green and blue are stored as 16bit
r, g, b = (las.red/256).astype(np.uint8), (las.green/256).astype(np.uint8), (las.blue/256).astype(np.uint8)
image = np.zeros((delta_y+1, delta_x+1, 3))
for i, val in enumerate(zip(tqdm(re_x), re_y)):
for k_x in range(-5, 6):
for k_y in range(-5, 6):
if val[0] + k_x < 0 or val[0] + k_x >= delta_x + 1:
k_x = 0
if val[1] + k_y < 0 or val[1] + k_y >= delta_y + 1:
k_y = 0
image[val[1]+k_y, val[0]+k_x] = [b[i], g[i], r[i]]
cv2.imwrite("test.png", image)
cv2.waitKey(0)
I found how to do it faster in numpy, but it can only do one colour at a time, so I decided to loop for multiple color but I think I am doing something wrong when I change the type to np.unit8 as python takes up to 50GB of RAM.
With numpy:
One colour:
def nu_pro(las):
x, y = las.X, las.Y
delta_x = max(x) - min(x)
delta_y = max(y) - min(y)
xs = x - min(x)
ys = y - min(y)
img_size = (delta_y+1, delta_x+1) # +1 for ravel_multi_index
bgr = np.array([(las.blue/256).astype(np.uint8), (las.green/256).astype(np.uint8), (las.red/256).astype(np.uint8)])
coords = np.stack((ys, xs))
abs_coords = np.ravel_multi_index(coords, img_size)
image = np.bincount(abs_coords, weights=color, minlength=img_size[1]*img_size[0])
image = image.reshape(img_size))
cv2.imwrite("test.png", image)
cv2.waitKey(0)
For rgb
def nu_pro_rgb(las):
x, y = las.X, las.Y
delta_x = max(x) - min(x)
delta_y = max(y) - min(y)
xs = x - min(x)
ys = y - min(y)
img_size = (delta_y+1, delta_x+1) # +1 for ravel_multi_index
rgb = np.array([(las.red/256).astype(np.uint8), (las.green/256).astype(np.uint8), (las.blue/256).astype(np.uint8)])
image = []
coords = np.stack((ys, xs))
abs_coords = np.ravel_multi_index(coords, img_size)
for i, color in enumerate(tqdm(rgb)):
img = np.bincount(abs_coords, weights=color, minlength=img_size[1]*img_size[0])
image.append(img.reshape(img_size))
image = np.uint8(np.array(image))
# I am probably messing up this transpose but I'll figure it out eventually
im = Image.fromarray(image.T, "RGB")
im.save("pil.png")
Any indication would be welcome :)
EDIT for clarification about the colours.
When there is overlapping, it should be the point with the highest z coordinates that should be displayed.
For the colouring, in the picture below, the points between A and B should be a colour gradient from A to B.
If it is like the yellow point, then an average of the neighbouring colour (without the black if present)
I hope I am making some sense.
To interpolate, there are lots of libraries.
This uses cubic interpolation, but it only works inside the convex hull, so the points outside the convex hull are taken from the nearest neighbor.
If you are interpolating GIS data, you may look on Krigging interpolation, which should interpolate outside the convex hull.
This code does not check that a point with lower Z is under one with higher Z. You have to delete those points to avoid having them interpolated.
from scipy.interpolate import griddata
import numpy as np
import matplotlib.pyplot as plt
import cv2
# create data
height, width = 256, 256
# generate a random sample of 1000 (x,y) coordinates and colors
x, y, z = np.random.randint(0, 256, size=(3, 1000))
color = np.random.randint(0, 256, size=(1000, 3))
# sort x,y,z by z in ascending order so the highest z is plotted over the lowest z
zSort = z.argsort()
x, y, z, color = x[zSort], y[zSort], z[zSort], color[zSort]
# interpolation
# generate a grid where the interpolation will be calculated
X, Y = np.meshgrid(np.arange(width), np.arange(height))
R = griddata(np.vstack((x, y)).T, color[:, 0], (X, Y), method='cubic')
Rlinear= griddata(np.vstack((x, y)).T, color[:, 0], (X, Y), method='nearest')
G = griddata(np.vstack((x, y)).T, color[:, 1], (X, Y), method='cubic')
Glinear= griddata(np.vstack((x, y)).T, color[:, 1], (X, Y), method='nearest')
B = griddata(np.vstack((x, y)).T, color[:, 2], (X, Y), method='cubic')
Blinear= griddata(np.vstack((x, y)).T, color[:, 2], (X, Y), method='nearest')
#Fill empty values with nearest neighbor
R[np.isnan(R)] = Rlinear[np.isnan(R)]
G[np.isnan(G)] = Glinear[np.isnan(G)]
B[np.isnan(B)] = Blinear[np.isnan(B)]
R = R/np.max(R)
G = G/np.max(G)
B = B/np.max(B)
interpolated = cv2.merge((R, G, B))
plt.imshow(interpolated)
plt.scatter(x, y, c=color/255, marker="s",s=1)
plt.show()
I do not have access to the format you use, so I show you how to rapidly plot points at x,y coordinates, and enlarge them with a kernel mask, and a color for each point
import numpy as np
import cv2
height, width = 256, 256
# generate a random sample of 1000 (x,y) coordinates and colors
x, y, = np.random.randint(0, 256, size=(2, 1000))
color = np.random.randint(0, 256, size=(1000, 3))
# generate a blank image
# int16 to manage overflow colors when convolving
pointsPlotted = np.zeros((height, width, 3), np.uint16)
# plot x,y,color into blankImage
pointsPlotted[y, x] = color
cv2.imshow("points", pointsPlotted.astype(np.uint8))
# convlove the image with a kernel of ones, size k
k = 5
kernel = np.ones((k, k), np.int16)
largerSquares = cv2.filter2D(src=pointsPlotted, ddepth=-1, kernel=kernel)
# limit max color to 255
largerSquares[largerSquares > 255] = 255
# Convert to uint8
largerSquares = largerSquares.astype(np.uint8)
cv2.imshow("Larger Squares", largerSquares)
Is this what you want?
On the overlaps, adds the colors (capped to 255)

aligning face image and merge in python cv2

I have a bunch of face image dataset (taken from http://vision.ucsd.edu/content/yale-face-database ) that I basically want to turn into a gif of the scramble suit from the movie scanner darkly ( http://2.bp.blogspot.com/-tRLWSOqh84Y/VSb_cF7sOoI/AAAAAAAAAWI/3XqT6d_exso/s1600/scramble%2Bsuit%2B2.gif ).
So far, I am able to take the images and cut them into face "pieces" in python in bulk.
The next step I am unable to do is to "align" these faces so that all the pieces form a face when they are merged or put back together.
Im also unsure how to merge or put them back together.
Once i have a bunch of images of randomly pieced together images, i am able to create the gif myself.
here is the code i have so far of taking the images, converting them to jpg and cutting them into necessary pieces (which was taken from here https://leslietj.github.io/2020/06/30/Automatic-Face-Crop-Using-Dlib/ ):
import sys
import dlib
from skimage import io
import numpy as np
import cv2
import matplotlib.pylab as plt
import math
from PIL import Image
import os
def arc_points(point1, point2, num_of_points):
points = []
center_x = (point1[0] + point2[0])/2
center_y = (point1[1] + point2[1])/2
radius = abs((point1[0] - point2[0])/2)
for i in range(num_of_points):
if i == 0:
continue
point = []
x = center_x + radius * math.cos(math.pi + i * math.pi / num_of_points)
y = center_y + radius * math.sin(math.pi + i * math.pi / num_of_points)
point.append(x)
point.append(y)
points.append(point)
return points
def get_landmarks(img,mode=1):
dets = detector(img, 1)
landmarks = np.zeros((34, 2))
for k, d in enumerate(dets):
shape = predictor(img, d)
#quarter face (#1)
if mode == 1:
landmarks[0]= (shape.part(0).x, shape.part(0).y)
landmarks[1] = (shape.part(1).x, shape.part(1).y)
landmarks[2] = (shape.part(2).x, shape.part(2).y)
landmarks[3] = (shape.part(30).x, shape.part(30).y)
landmarks[4] = (shape.part(29).x, shape.part(29).y)
landmarks[5] = (shape.part(28).x, shape.part(28).y)
point1 = [shape.part(0).x, shape.part(0).y]
point2 = [shape.part(28).x, shape.part(28).y]
points = arc_points(point1, point2, 29)
for i in range(len(points)):
landmarks[33 - i] = (points[i][0], points[i][1])
#half face (#2)
if mode == 2:
landmarks[0] = (shape.part(0).x, shape.part(0).y)
landmarks[1] = (shape.part(1).x, shape.part(1).y)
landmarks[2] = (shape.part(2).x, shape.part(2).y)
landmarks[3] = (shape.part(14).x, shape.part(14).y)
landmarks[4] = (shape.part(15).x, shape.part(15).y)
landmarks[5] = (shape.part(16).x, shape.part(16).y)
point1 = [shape.part(0).x, shape.part(0).y]
point2 = [shape.part(16).x, shape.part(16).y]
points = arc_points(point1, point2, 29)
#print(points)
for i in range(len(points)):
#print(33-i)
landmarks[33 - i] = (points[i][0], points[i][1])
if mode == 3:
#3/4 face (#3)
for i in range(9):
landmarks[i] = (shape.part(i).x, shape.part(i).y)
landmarks[9] = (shape.part(31).x, shape.part(31).y)
landmarks[10] = (shape.part(14).x, shape.part(14).y)
landmarks[11] = (shape.part(15).x, shape.part(15).y)
landmarks[12] = (shape.part(16).x, shape.part(16).y)
point1 = [shape.part(0).x, shape.part(0).y]
point2 = [shape.part(16).x, shape.part(16).y]
points = arc_points(point1, point2, 22)
for i in range(len(points)):
landmarks[33 - i] = (points[i][0], points[i][1])
#full face (#4)
if mode == 4:
for i in range(17):
landmarks[i] = (shape.part(i).x, shape.part(i).y)
point1 = [shape.part(0).x, shape.part(0).y]
point2 = [shape.part(16).x, shape.part(16).y]
points = arc_points(point1, point2, 18)
for i in range(len(points)):
landmarks[33 - i] = (points[i][0], points[i][1])
return landmarks
def inside(X,Y,Region):
j=len(Region)-1
flag=False
for i in range(len(Region)):
if (Region[i][1]<Y and Region[j][1]>=Y or Region[j][1]<Y and Region[i][1]>=Y):
if (Region[i][0] + (Y - Region[i][1]) / (Region[j][1] - Region[i][1]) * (Region[j][0] - Region[i][0]) < X):
flag =not flag
j=i
return flag
count=0
files = os.listdir('yalefaces')
for filename in files:
if filename.endswith('glasses') or filename.endswith('happy') or filename.endswith('noglasses') or filename.endswith('normal'):
path = os.path.join('yalefaces',filename)
# importing the image
im = Image.open(path)
# converting to jpg
rgb_im = im.convert("RGB")
# exporting the image
rgb_im.save('temp.jpg')
count+=1
path = 'temp.jpg'
for im in range(1,5):
#path = 'subject01.jpg'
detector = dlib.get_frontal_face_detector()
# the .dat file can be downloaded following this link:
# https://sourceforge.net/projects/dclib/files/dlib/v18.10/shape_predictor_68_face_landmarks.dat.bz2/download
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
img = io.imread(path)
region = get_landmarks(img,mode=im)
shape = list(img.shape)
cropped_img = img.copy()
for i in range(shape[0]):
for j in range(shape[1]):
if not inside(j, i, region):
#print(img[0])
cropped_img[i, j] = (img[0,0][0], img[0,0][1], img[0,0][2]) # the RGB values of the background
cropped_img = cv2.cvtColor(cropped_img, cv2.COLOR_BGR2GRAY)
cv2.imwrite(str(count).zfill(3)+'-'+str(im).zfill(2)+'.jpg', cropped_img)
since this is several steps of pre-processing:
align faces using this script https://pyimagesearch.com/2017/05/22/face-alignment-with-opencv-and-python/
cut up the faces and put them together. as mentioned before, i was doing a cv2.add which is not what i want. i actually want the layers to stack up and if there is anything underneath, ignore it. cv2.add doesnt do this so i had to make my own. so if i had two layers and i want to stack them up so that the first layer on top is the one that takes priority and the bottom layer is ignored if there is anything above it.
def reduction(layer1,layer2):
for i in range(0,layer1.shape[0]):
for j in range(0,layer1.shape[1]):
pixel1 = layer1.item(i, j)
pixel2 = layer2.item(i, j)
if layer2[i,j] != 255:
layer1[i,j]=255
return layer1
layer2 = reduction(layer2,layer1)
for i in range(0,layer1.shape[0]):
for j in range(0,layer1.shape[1]):
pixel = layer2[i,j]
if pixel != 255:
layer1[i,j]=layer2[i,j]
and thats it. i didnt realize images are just numpy arrays so i can just manipulate the arrays directly.

Count red pixel values and plot histogram in Python

I have a set of images that are located in 3 separate folders, based on their Type. I want to iterate through every Type and count the red pixel values of every image. I have set a limit for red, being in range from 200 to 256. I want to create histograms for each type and later cluster the histogram and discriminate between the 3 classes. My experience with Python is very limited and I am stuck at how to isolate and count the red pixel values. I have attached my code and the resulting histogram for Type 1, which is a straight line. Could someone help on this?
import numpy as np
import cv2
import os.path
import glob
import matplotlib.pyplot as plt
## take the image, compute sum of all row colors and return the percentage
#iterate through every Type
for t in [1]:
#load_files
files = glob.glob(os.path.join("..", "data", "train", "Type_{}".format(t), "*.jpg"))
no_files = len(files)
#iterate and read
for n, file in enumerate(files):
try:
image = cv2.imread(file)
hist = cv2.calcHist([img], [0], None, [56], [200, 256])
print(file, t, "-files left", no_files - n)
except Exception as e:
print(e)
print(file)
plt.plot(hist)
plt.show()
This is the solution I came up with. I have taken the liberty to refactor and simplify your code a bit.
import os
import glob
import numpy as np
import matplotlib.pyplot as plt
from skimage import io
root = 'C:\Users\you\imgs' # Change this appropriately
folders = ['Type_1', 'Type_2', 'Type_3']
extension = '*.bmp' # Change if necessary
threshold = 150 # Adjust to fit your neeeds
n_bins = 5 # Tune these values to customize the plot
width = 2.
colors = ['cyan', 'magenta', 'yellow']
edges = np.linspace(0, 100, n_bins+1)
centers = .5*(edges[:-1]+ edges[1:])
# This is just a convenience class used to encapsulate data
class img_type(object):
def __init__(self, folder, color):
self.folder = folder
self.percents = []
self.color = color
lst = [img_type(f, c) for f, c in zip(folders, colors)]
fig, ax = plt.subplots()
for n, obj in enumerate(lst):
filenames = glob.glob(os.path.join(root, obj.folder, extension))
for fn in filenames:
img = io.imread(fn)
red = img[:, :, 0]
obj.percents.append(100.*np.sum(red >= threshold)/red.size)
h, _ = np.histogram(obj.percents, bins=edges)
h = np.float64(h)
h /= h.sum()
h *= 100.
ax.bar(centers + (n - .5*len(lst))*width, h, width, color=obj.color)
ax.legend(folders)
ax.set_xlabel('% of pixels whose red component is >= threshold')
ax.set_ylabel('% of images')
plt.show()
Notice that I have I used scikit-image rather than OpenCV to read the images. If this is not an option for you, insert import cv2 and change:
img = io.imread(fn)
red = img[:, :, 0]
to:
img = cv2.imread(fn)
red = img[:, :, 2]

Maximum likelihood pixel classification in python opencv

I would like to perform pixel classification on RGB images based on input training samples of given number of classes. So I have e.g. 4 classes containing pixels (r,g,b) thus the goal is to segment the image into four phases.
I found that python opencv2 has the Expectation maximization algorithm which could do the job. But unfortunately I did not find any tutorial or material which can explain me (since I am beginner) how to work with the algorithm.
Could you please propose any kind of tutorial which can be used as starting point?
Update...another approach for the code below:
**def getsamples(img):
x, y, z = img.shape
samples = np.empty([x * y, z])
index = 0
for i in range(x):
for j in range(y):
samples[index] = img[i, j]
index += 1
return samples
def EMSegmentation(img, no_of_clusters=2):
output = img.copy()
colors = np.array([[0, 11, 111], [22, 22, 22]])
samples = getsamples(img)
#em = cv2.ml.EM_create()
em = cv2.EM(no_of_clusters)
#em.setClustersNumber(no_of_clusters)
#em.trainEM(samples)
em.train(samples)
x, y, z = img.shape
index = 0
for i in range(x):
for j in range(y):
result = em.predict(samples[index])[0][1]
#print(result)
output[i][j] = colors[result]
index = index + 1
return output
img = cv2.imread('00.jpg')
smallImg = small = cv2.resize(img, (0,0), fx=0.5, fy=0.5)
output = EMSegmentation(img)
smallOutput = cv2.resize(output, (0,0), fx=0.5, fy=0.5)
cv2.imshow('image', smallImg)
cv2.imshow('EM', smallOutput)
cv2.waitKey(0)
cv2.destroyAllWindows()**
convert C++ to python source
import cv2
import numpy as np
def getsamples(img):
x, y, z = img.shape
samples = np.empty([x * y, z])
index = 0
for i in range(x):
for j in range(y):
samples[index] = img[i, j]
index += 1
return samples
def EMSegmentation(img, no_of_clusters=2):
output = img.copy()
colors = np.array([[0, 11, 111], [22, 22, 22]])
samples = getsamples(img)
em = cv2.ml.EM_create()
em.setClustersNumber(no_of_clusters)
em.trainEM(samples)
means = em.getMeans()
covs = em.getCovs() # Known bug: https://github.com/opencv/opencv/pull/4232
x, y, z = img.shape
distance = [0] * no_of_clusters
for i in range(x):
for j in range(y):
for k in range(no_of_clusters):
diff = img[i, j] - means[k]
distance[k] = abs(np.dot(np.dot(diff, covs[k]), diff.T))
output[i][j] = colors[distance.index(max(distance))]
return output
img = cv2.imread('dinosaur.jpg')
output = EMSegmentation(img)
cv2.imshow('image', img)
cv2.imshow('EM', output)
cv2.waitKey(0)
cv2.destroyAllWindows()

How to Split Image Into Multiple Pieces in Python

I'm trying to split a photo into multiple pieces using PIL.
def crop(Path,input,height,width,i,k,x,y,page):
im = Image.open(input)
imgwidth = im.size[0]
imgheight = im.size[1]
for i in range(0,imgheight-height/2,height-2):
print i
for j in range(0,imgwidth-width/2,width-2):
print j
box = (j, i, j+width, i+height)
a = im.crop(box)
a.save(os.path.join(Path,"PNG","%s" % page,"IMG-%s.png" % k))
k +=1
but it doesn't seem to be working. It splits the photo but not in an exact way (you can try it).
Splitting image to tiles of MxN pixels (assuming im is numpy.ndarray):
tiles = [im[x:x+M,y:y+N] for x in range(0,im.shape[0],M) for y in range(0,im.shape[1],N)]
In the case you want to split the image to four pieces:
M = im.shape[0]//2
N = im.shape[1]//2
tiles[0] holds the upper left tile
Edit: I believe this answer missed the intent to cut an image into rectangles in columns and rows. This answer cuts only into rows. It looks like other answers cut in columns and rows.
Simpler than all these is to use a wheel someone else invented :) It may be more involved to set up, but then it's a snap to use.
These instructions are for Windows 7; they may need to be adapted for other OSs.
Get and install pip from here.
Download the install archive, and extract it to your root Python installation directory. Open a console and type (if I recall correctly):
python get-pip.py install
Then get and install the image_slicer module via pip, by entering the following command at the console:
python -m pip install image_slicer
Copy the image you want to slice into the Python root directory, open a python shell (not the "command line"), and enter these commands:
import image_slicer
image_slicer.slice('huge_test_image.png', 14)
The beauty of this module is that it
Is installed in python
Can invoke an image split with two lines of code
Accepts any even number as an image slice parameter (e.g. 14 in this example)
Takes that parameter and automagically splits the given image into so many slices, and auto-saves the resultant numbered tiles in the same directory, and finally
Has a function to stitch the image tiles back together (which I haven't yet tested); files apparently must be named after the convention which you will see in the split files after testing the image_slicer.slice function.
from PIL import Image
def crop(path, input, height, width, k, page, area):
im = Image.open(input)
imgwidth, imgheight = im.size
for i in range(0,imgheight,height):
for j in range(0,imgwidth,width):
box = (j, i, j+width, i+height)
a = im.crop(box)
try:
o = a.crop(area)
o.save(os.path.join(path,"PNG","%s" % page,"IMG-%s.png" % k))
except:
pass
k +=1
As an alternative solution, we will construct the tiles by generating a grid of coordinates using itertools.product. We will ignore partial tiles on the edges, only iterating through the cartesian product between the two intervals, i.e. range(0, h-h%d, d) X range(0, w-w%d, d).
Given filename: the image file name, d: the tile size, dir_in: the path to the directory containing the image, and dir_out: the directory where tiles will be outputted:
from PIL import Image
from itertools import product
def tile(filename, dir_in, dir_out, d):
name, ext = os.path.splitext(filename)
img = Image.open(os.path.join(dir_in, filename))
w, h = img.size
grid = product(range(0, h-h%d, d), range(0, w-w%d, d))
for i, j in grid:
box = (j, i, j+d, i+d)
out = os.path.join(dir_out, f'{name}_{i}_{j}{ext}')
img.crop(box).save(out)
crop would be a more reusable
function if you separate the
cropping code from the
image saving
code. It would also make the call
signature simpler.
im.crop returns a
Image._ImageCrop instance. Such
instances do not have a save method.
Instead, you must paste the
Image._ImageCrop instance onto a
new Image.Image
Your ranges do not have the right
step sizes. (Why height-2 and not
height? for example. Why stop at
imgheight-(height/2)?).
So, you might try instead something like this:
import Image
import os
def crop(infile,height,width):
im = Image.open(infile)
imgwidth, imgheight = im.size
for i in range(imgheight//height):
for j in range(imgwidth//width):
box = (j*width, i*height, (j+1)*width, (i+1)*height)
yield im.crop(box)
if __name__=='__main__':
infile=...
height=...
width=...
start_num=...
for k,piece in enumerate(crop(infile,height,width),start_num):
img=Image.new('RGB', (height,width), 255)
img.paste(piece)
path=os.path.join('/tmp',"IMG-%s.png" % k)
img.save(path)
Here is a concise, pure-python solution that works in both python 3 and 2:
from PIL import Image
infile = '20190206-135938.1273.Easy8thRunnersHopefully.jpg'
chopsize = 300
img = Image.open(infile)
width, height = img.size
# Save Chops of original image
for x0 in range(0, width, chopsize):
for y0 in range(0, height, chopsize):
box = (x0, y0,
x0+chopsize if x0+chopsize < width else width - 1,
y0+chopsize if y0+chopsize < height else height - 1)
print('%s %s' % (infile, box))
img.crop(box).save('zchop.%s.x%03d.y%03d.jpg' % (infile.replace('.jpg',''), x0, y0))
Notes:
The crops that go over the right and bottom of the original image are adjusted to the original image limit and contain only the original pixels.
It's easy to choose a different chopsize for w and h by using two chopsize vars and replacing chopsize as appropriate in the code above.
Not sure if this is the most efficient answer, but it works for me:
import os
import glob
from PIL import Image
Image.MAX_IMAGE_PIXELS = None # to avoid image size warning
imgdir = "/path/to/image/folder"
# if you want file of a specific extension (.png):
filelist = [f for f in glob.glob(imgdir + "**/*.png", recursive=True)]
savedir = "/path/to/image/folder/output"
start_pos = start_x, start_y = (0, 0)
cropped_image_size = w, h = (500, 500)
for file in filelist:
img = Image.open(file)
width, height = img.size
frame_num = 1
for col_i in range(0, width, w):
for row_i in range(0, height, h):
crop = img.crop((col_i, row_i, col_i + w, row_i + h))
name = os.path.basename(file)
name = os.path.splitext(name)[0]
save_to= os.path.join(savedir, name+"_{:03}.png")
crop.save(save_to.format(frame_num))
frame_num += 1
This is mostly based on DataScienceGuy answer here
Here is a late answer that works with Python 3
from PIL import Image
import os
def imgcrop(input, xPieces, yPieces):
filename, file_extension = os.path.splitext(input)
im = Image.open(input)
imgwidth, imgheight = im.size
height = imgheight // yPieces
width = imgwidth // xPieces
for i in range(0, yPieces):
for j in range(0, xPieces):
box = (j * width, i * height, (j + 1) * width, (i + 1) * height)
a = im.crop(box)
try:
a.save("images/" + filename + "-" + str(i) + "-" + str(j) + file_extension)
except:
pass
Usage:
imgcrop("images/testing.jpg", 5, 5)
Then the images will be cropped into pieces according to the specified X and Y pieces, in my case 5 x 5 = 25 pieces
Here is another solution, just using NumPy built-in np.array_split :
def divide_img_blocks(img, n_blocks=(5, 5)):
horizontal = np.array_split(img, n_blocks[0])
splitted_img = [np.array_split(block, n_blocks[1], axis=1) for block in horizontal]
return np.asarray(splitted_img, dtype=np.ndarray).reshape(n_blocks)
It returns a NumPy array with the dimension passed as n_blocks.
Each element of the array is a block, so to access each block and save it as an image you should write something like the following:
result = divide_img_blocks(my_image)
for i in range(result.shape[0]):
for j in range(result.shape[1]):
cv2.imwrite(f"my_block_{i}_{j}.jpg", result[i,j])
This answer is very fast, faster than #Nir answer, which among the posted ones was the cleanest. Additionally is almost three orders of magnitude faster than the suggested package (i.e. image_slicer).
Time taken by divide_img_blocks: 0.0009832382202148438
Time taken by Nir answer: 0.002960681915283203
Time taken by image_slicer.slice: 0.4419238567352295
Hope it can still be useful.
I find it easier to skimage.util.view_as_windows or `skimage.util.view_as_blocks which also allows you to configure the step
http://scikit-image.org/docs/dev/api/skimage.util.html?highlight=view_as_windows#skimage.util.view_as_windows
import os
import sys
from PIL import Image
savedir = r"E:\new_mission _data\test"
filename = r"E:\new_mission _data\test\testing1.png"
img = Image.open(filename)
width, height = img.size
start_pos = start_x, start_y = (0, 0)
cropped_image_size = w, h = (1024,1024)
frame_num = 1
for col_i in range(0, width, w):
for row_i in range(0, height, h):
crop = img.crop((col_i, row_i, col_i + w, row_i + h))
save_to= os.path.join(savedir, "testing_{:02}.png")
crop.save(save_to.format(frame_num))
frame_num += 1
For anyone looking for a simple approach to this, here is a simple working function for splitting an image into NxN sections.
def slice_image(filename, N):
i = Image.open(filename)
width = i.width
height = i.height
for x in range(N):
for y in range(N):
index = (x * pieces) + 1 + y
img = i.crop((x * width/N, y * height/N,
x * width/N+ width/N, y * height/N+ height/N))
img.save(f"{filename}_sliced_{index}.jpeg")
Thanks #Ivan for teaching me something about itertools and grids. Came here to split up tomographic 3D image data (tif-files) into smaller regions for evaluation. I adapted the script to 3D-TIF files (using the tiffile library) and added a "centered" approach. So the tiles don't start in the upper-left corner but are centered and crop too small tiles at the borders at each direction. Maybe this also help other people.
from itertools import product
import tifffile as tif
import numpy as np
path = 'PATH'
filename= 'FILENAME.tif'
img = tif.imread(path+filename)
depth, height, width = img.shape
tilesize = 100
grid = product(range(int((depth%tilesize)/2), int(depth-(depth%tilesize)/2), tilesize),
range(int((width%tilesize)/2), int(width-((width%tilesize)/2)), tilesize),
range(int((height%tilesize)/2), int(height-(height%tilesize)/2), tilesize))
for z,y,x in grid:
crop = img[z:z+tilesize, y:y+tilesize, x:x+tilesize]
tif.imwrite(path+filename+f'{z:04d}z_{y:04d}y_{x:04d}x.tif', crop, dtype = np.uint8)
This is my script tools, it is very sample to splite css-sprit image into icons:
Usage: split_icons.py img dst_path width height
Example: python split_icons.py icon-48.png gtliu 48 48
Save code into split_icons.py :
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import os
import sys
import glob
from PIL import Image
def Usage():
print '%s img dst_path width height' % (sys.argv[0])
sys.exit(1)
if len(sys.argv) != 5:
Usage()
src_img = sys.argv[1]
dst_path = sys.argv[2]
if not os.path.exists(sys.argv[2]) or not os.path.isfile(sys.argv[1]):
print 'Not exists', sys.argv[2], sys.argv[1]
sys.exit(1)
w, h = int(sys.argv[3]), int(sys.argv[4])
im = Image.open(src_img)
im_w, im_h = im.size
print 'Image width:%d height:%d will split into (%d %d) ' % (im_w, im_h, w, h)
w_num, h_num = int(im_w/w), int(im_h/h)
for wi in range(0, w_num):
for hi in range(0, h_num):
box = (wi*w, hi*h, (wi+1)*w, (hi+1)*h)
piece = im.crop(box)
tmp_img = Image.new('L', (w, h), 255)
tmp_img.paste(piece)
img_path = os.path.join(dst_path, "%d_%d.png" % (wi, hi))
tmp_img.save(img_path)
I tried the solutions above, but sometimes you just gotta do it yourself.
Might be off by a pixel in some cases but works fine in general.
import matplotlib.pyplot as plt
import numpy as np
def image_to_tiles(im, number_of_tiles = 4, plot=False):
"""
Function that splits SINGLE channel images into tiles
:param im: image: single channel image (NxN matrix)
:param number_of_tiles: squared number
:param plot:
:return tiles:
"""
n_slices = np.sqrt(number_of_tiles)
assert int(n_slices + 0.5) ** 2 == number_of_tiles, "Number of tiles is not a perfect square"
n_slices = n_slices.astype(np.int)
[w, h] = cropped_npy.shape
r = np.linspace(0, w, n_slices+1)
r_tuples = [(np.int(r[i]), np.int(r[i+1])) for i in range(0, len(r)-1)]
q = np.linspace(0, h, n_slices+1)
q_tuples = [(np.int(q[i]), np.int(q[i+1])) for i in range(0, len(q)-1)]
tiles = []
for row in range(n_slices):
for column in range(n_slices):
[x1, y1, x2, y2] = *r_tuples[row], *q_tuples[column]
tiles.append(im[x1:y1, x2:y2])
if plot:
fig, axes = plt.subplots(n_slices, n_slices, figsize=(10,10))
c = 0
for row in range(n_slices):
for column in range(n_slices):
axes[row,column].imshow(tiles[c])
axes[row,column].axis('off')
c+=1
return tiles
Hope it helps.
I would suggest to use multiprocessing instead of a regular for loop as follows:
from PIL import Image
import os
def crop(infile,height,width):
im = Image.open(infile)
imgwidth, imgheight = im.size
for i in range(imgheight//height):
for j in range(imgwidth//width):
box = (j*width, i*height, (j+1)*width, (i+1)*height)
yield im.crop(box)
def til_image(infile):
infile=...
height=...
width=...
start_num=...
for k,piece in enumerate(crop(infile,height,width),start_num):
img=Image.new('RGB', (height,width), 255)
img.paste(piece)
path=os.path.join('/tmp',"IMG-%s.png" % k)
img.save(path)
from multiprocessing import Pool, cpu_count
try:
pool = Pool(cpu_count())
pool.imap_unordered(tile_image, os.listdir(root), chunksize=4)
finally:
pool.close()
the easiest way:
import image_slicer
image_slicer.slice('/Address of image for exp/A1.png',16)
this command splits the image into 16 slices and saves them in the directory that the input image is there.
you should first install image_slicer:
pip install image_slicer
Splitting an image into squares of a specific size
I adapted a solution so that it accepts a specific tile size instead of an amount of tiles because I needed to cut the image up into a grid of 32px squares.
The parameters are the image_path and the size of the tiles in pixels.
I tried to make the code as readable as possible.
# Imports
from PIL import Image
import os
import random
# Function
def image_to_tiles(im, tile_size = 32):
"""
Function that splits an image into tiles
:param im: image: image path
:param tile_size: width in pixels of a tile
:return tiles:
"""
image = Image.open(im)
w = image.width
h = image.height
row_count = np.int64((h-h%tile_size)/tile_size)
col_count = np.int64((w-w%tile_size)/tile_size)
n_slices = np.int64(row_count*col_count)
# Image info
print(f'Image: {im}')
print(f'Dimensions: w:{w} h:{h}')
print(f'Tile count: {n_slices}')
r = np.linspace(0, w, row_count+1)
r_tuples = [(np.int64(r[i]), np.int64(r[i])+tile_size) for i in range(0, len(r)-1)]
q = np.linspace(0, h, col_count+1)
q_tuples = [(np.int64(q[i]), np.int64(q[i])+tile_size) for i in range(0, len(q)-1)]
#print(f'r_tuples:{r_tuples}\n\nq_tuples:{q_tuples}\n')
tiles = []
for row in range(row_count):
for column in range(col_count):
[y1, y2, x1, x2] = *r_tuples[row], *q_tuples[column]
x2 = x1+tile_size
y2 = y1+tile_size
tile_image = image.crop((x1,y1,x2,y2))
tile_coords = {'x1':x1,'y1':y1,'x2':x2,'y2':y2}
tiles.append({'image':tile_image,'coords':tile_coords})
return tiles
# Testing:
img_path ='/home/user/path/to/image.jpg'
tiles = image_to_tiles(img_path)
for i in range(20):
tile = random.choice(tiles)
tile['image'].show()
you can use numpy stride tricks to achive this, but be careful, as this function has to be used with extreme care (doc)
import numpy as np
from numpy.lib.stride_tricks import as_strided
def img_pieces(img, piece_size):
height, width, chanels = img.shape
n_bytes = img.strides[-1]
return np.reshape(
as_strided(
img,
(
height // piece_size,
width // piece_size,
piece_size,
piece_size,
chanels
),
(
n_bytes * chanels * width * piece_size,
n_bytes * chanels * piece_size,
n_bytes * chanels * width,
n_bytes * chanels,
n_bytes
)
),
(
-1,
piece_size,
piece_size,
chanels
)
)
Here's my attempt on a grayscale image with only numpy based on the solution from here, with some minor tweaks (adding channels) it might suit your needs:
import numpy as np
# Seperate grayscale images to w * h tiles, add padding with zeros if image not scaled
def to_tiles(arr: np.ndarray, tilesize: tuple[int, int]) -> np.ndarray:
def f(x: tuple[int, int]) -> tuple[int, int]:
tmp = list(x)
if tmp[1] > 0:
tmp[0] = tmp[0] + 1
return tuple(tmp)
# # Stride Implementation
# bytelength = np.int8(np.divide(arr.nbytes, arr.size))
assert arr.ndim == 2, "array must be 2d (grayscale) image"
a_h, a_w = arr.shape
h, w = tilesize
assert a_h > h, "tile height is larger than arr height"
assert a_w > w, "tile width is larger than arr width"
row, row_r = f(np.divmod(a_h, h))
col, col_r = f(np.divmod(a_w, w))
arr = np.pad(
arr,
[
(
np.int8(np.ceil(np.divide(h-row_r, 2))) if row_r != 0 else 0,
np.int8(np.floor(np.divide(h-row_r, 2))) if row_r != 0 else 0,
),
(
np.int8(np.ceil(np.divide(w-col_r, 2))) if col_r != 0 else 0,
np.int8(np.floor(np.divide(w-col_r, 2))) if col_r != 0 else 0,
),
],
"constant",
constant_values=(0),
)
# # Stride Implementation
# arr = np.lib.stride_tricks.as_strided(
# arr, shape=(row, col, h, w), strides=(h*a_w*bytelength, w*bytelength, a_w*bytelength, bytelength)
# )
arr = arr.reshape(row, h, col, w).swapaxes(1, 2)
arr = arr.reshape(-1, h, w)
return arr
Here's an example of the result. Image from FUNSD dataset.
def split(img,nbxsplit,nbysplit):
xdemi=int(img.shape[0]/nbxsplit)
ydemi=int(img.shape[1]/nbxsplit)
arr=[]
for i in range(0,img.shape[0]-xdemi+1,xdemi):
for j in range(0,img.shape[1]-ydemi+1,ydemi):
arr.append(img[i:i+xdemi][j:j+ydemi])
a=np.reshape(a,(img.shape[0]-xdemi,img.shape[1]-xdemi))
return a
Not sure if it's still relevant, but my attempt is following:
(I am assuming the image is a numpy array. I am not using Pil or anything, since i didn't want to have any dependencies other than numpy.)
def cut_image_grid(image:np.ndarray, grid_size:int=4):
height, width = image.shape[0], image.shape[1]
piece_height, piece_width = height//grid_size, width//grid_size
pieces = []
for i in range(grid_size):
for j in range(grid_size):
y = i * piece_height
x = j * piece_width
h = (i+1) * piece_height if i < grid_size else None
w = (j+1) * piece_width if j < grid_size else None
piece = image[y:h, x:w]
pieces.append(piece)
return np.array(pieces)
As input the function is receiving a numpy image and an integer (which you could also turn into tuples, but i wanted to have evenly spaced grid cells always with same amount of cells row and column wise).
At first, the code calculates the width and height of the cells based on the given grid_size. After that the code iterates over all rows and columns and generates x, y Coordinates, as well as x0 and y0 (y+height, x+width) for defining the cells.
Every cell is saved as a list into pieces, which is then transformed into a numpy array and returned.
import cv2
def crop_image(image_path, output_path):
im = cv2.imread(os.listdir()[2])
imgheight=im.shape[0]
imgwidth=im.shape[1]
y1 = 0
M = 2000
N = 2000
for y in range(0,imgheight,M):
for x in range(0, imgwidth, N):
y1 = y + M
x1 = x + N
tiles = im[y:y+M,x:x+N]
if tiles.shape[0] < 100 or tiles.shape[1]<100:
continue
cv2.rectangle(im, (x, y), (x1, y1), (0, 255, 0))
cv2.imwrite(output_path + str(x) + '_' + str(y)+"{}.png".format(image_path),tiles)
crop_image(os.listdir()[2], './cutted/')

Categories