We Keep Coding

Kmean algorithm on high resolution images

I have an image with 22500x55000x3 shape and I want to apply kmean algorithm on this image. Unfortunatelly it takes so much time even if I run the algorithm in a server. What can be done for this situation ?
Here the code I used.
import os
os.environ["OPENCV_IO_MAX_IMAGE_PIXELS"] = pow(2,40).__str__()
import cv2
import numpy
import json
import matplotlib.pyplot as plt
image = cv2.imread("images/2021/true_color_08.jpg")
mask = cv2.imread("images/2021/09/all_08.jpg")
image = cv2.bitwise_and(image,mask, dst = image)
pixel_values = image.reshape((-1, 3))
# convert to float
pixel_values = numpy.float32(pixel_values)
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 100, 0.2)
k = 4
_, labels, (centers) = cv2.kmeans(pixel_values, k, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS)
# convert back to 8 bit values
centers = numpy.uint8(centers)
centers[0] = [255,255,255]
centers[1] = [255,0,0]
centers[2] = [0,255,0]
centers[3] = [0,0,255]
# flatten the labels array
labels = labels.flatten()
segmented_image = centers[labels]
# reshape back to the original image dimension
segmented_image = segmented_image.reshape(image.shape)
# show the image
plt.imshow(segmented_image)
plt.show()

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

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()

How can I change the color of kmeans clusters in image segmentation

I tried to perform image segmentation using kmeans clustering.
I want to have control concerning the color of classes.How i can do that ?
# convert to np.float32
Z = np.float32(Z)
# define criteria, number of clusters(K) and apply kmeans()
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
K = 2
ret,label,center=cv2.kmeans(Z,K,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)
# Now convert back into uint8, and make original image
center = np.uint8(center)
res = center[label.flatten()]
res2 = res.reshape((img.shape))
#cv2.imshow('res2',res2)
#cv2.waitKey(0)
#cv2.destroyAllWindows()
Image.fromarray(res2).save(f + 'kmeans.png', "png", quality=100)
kmean()

I don't know what you want to control with 2 centers.
If you want to get binary map, you can follow here:
# convert to np.float32
Z = np.float32(Z)
# define criteria, number of clusters(K) and apply kmeans()
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
K = 2
ret,label,center=cv2.kmeans(Z,K,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)
# get the most popular color and specify it is black
black_color = np.argmax(np.bincount(label.flatten()))
# generate binary map with white color
center = np.ones((K,1), dtype = 'uint8') * 255
center[black_color] = [0]
res = center[label.flatten()]
res2 = res.reshape((image_text.shape[0], image_text.shape[1], 1))
return res2
You can change any color you want, not just white and black. Hope to help you

How make eye and nose bigger or smaller in opencv and python

I used the following code to select nose in OpenCV and Python i searched a lot of to find a way to change the size of nose and save as a other image but i didn't find anything is there anybody to help me to do this.
import cv2
import numpy as np
import dlib
img = cv2.imread('1.jpg')
img = cv2.resize(img,(0,0),None,0.5,0.5)
imgOriginal = img.copy()
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
def createBox(img,points,scale=5):
bbox = cv2.boundingRect(points)
x,y,w,h = bbox
imgCrop = img[y:y+h,x:x+w]
imgCrop = cv2.resize(imgCrop,(0,0),None,scale,scale)
return imgCrop
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
faces = detector(imgGray)
for face in faces:
x1,y1 = face.left(),face.top()
x2,y2 = face.right(),face.bottom()
imgOriginal = cv2.rectangle(img,(x1,y1),(x2,y2),(0,255,0),1)
landmarks = predictor(imgGray,face)
myPoints=[]
for n in range(68):
x = landmarks.part(n).x
y = landmarks.part(n).y
myPoints.append([x,y])
#cv2.circle(imgOriginal,(x,y),5,(50,50,255),cv2.FILLED)
#cv2.putText(imgOriginal,str(n),(x,y-10),cv2.FONT_HERSHEY_COMPLEX_SMALL,0.8,(0,0,255),1)
myPoints = np.array(myPoints)
#nose points to select
#nose_points = myPoints[27:35]
print(myPoints)
cv2_imshow(imgOriginal)
cv2.waitKey(0)
thanks in advance

Here is one way using a spherical (bubble) warp in a local region in Python/OpenCV.
- Define region center and radius and amount of spherical distortion
- Crop the image for that center and radius
- Compute the spherical distortion x and y displacement maps and a binary mask
- Apply the distortion maps using cv2.remap
- Antialias the mask
- Merge the distorted and cropped image using the mask
- Insert that merged image into the original image
- Save the results
Input:
import numpy as np
import cv2
import math
import skimage.exposure
img = cv2.imread("portrait_of_mussorgsky2.jpg")
# set location and radius
cx = 130
cy = 109
radius = 30
# set distortion gain
gain = 1.5
# crop image
crop = img[cy-radius:cy+radius, cx-radius:cx+radius]
# get dimensions
ht, wd = crop.shape[:2]
xcent = wd / 2
ycent = ht / 2
rad = min(xcent,ycent)
# set up the x and y maps as float32
map_x = np.zeros((ht, wd), np.float32)
map_y = np.zeros((ht, wd), np.float32)
mask = np.zeros((ht, wd), np.uint8)
# create map with the spherize distortion formula --- arcsin(r)
# xcomp = arcsin(r)*x/r; ycomp = arsin(r)*y/r
for y in range(ht):
Y = (y - ycent)/ycent
for x in range(wd):
X = (x - xcent)/xcent
R = math.hypot(X,Y)
if R == 0:
map_x[y, x] = x
map_y[y, x] = y
mask[y,x] = 255
elif R >= .90: # avoid extreme blurring near R = 1
map_x[y, x] = x
map_y[y, x] = y
mask[y,x] = 0
elif gain >= 0:
map_x[y, x] = xcent*X*math.pow((2/math.pi)*(math.asin(R)/R), gain) + xcent
map_y[y, x] = ycent*Y*math.pow((2/math.pi)*(math.asin(R)/R), gain) + ycent
mask[y,x] = 255
elif gain < 0:
gain2 = -gain
map_x[y, x] = xcent*X*math.pow((math.sin(math.pi*R/2)/R), gain2) + xcent
map_y[y, x] = ycent*Y*math.pow((math.sin(math.pi*R/2)/R), gain2) + ycent
mask[y,x] = 255
# remap using map_x and map_y
bump = cv2.remap(crop, map_x, map_y, cv2.INTER_LINEAR, borderMode = cv2.BORDER_CONSTANT, borderValue=(0,0,0))
# antialias edge of mask
# (pad so blur does not extend to edges of image, then crop later)
blur = 7
mask = cv2.copyMakeBorder(mask, blur,blur,blur,blur, borderType=cv2.BORDER_CONSTANT, value=(0))
mask = cv2.GaussianBlur(mask, (0,0), sigmaX=blur, sigmaY=blur, borderType = cv2.BORDER_DEFAULT)
h, w = mask.shape
mask = mask[blur:h-blur, blur:w-blur]
mask = cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR)
mask = skimage.exposure.rescale_intensity(mask, in_range=(127.5,255), out_range=(0,1))
# merge bump with crop using grayscale (not binary) mask
bumped = (bump * mask + crop * (1-mask)).clip(0,255).astype(np.uint8)
# insert bumped image into original
result = img.copy()
result[cy-radius:cy+radius, cx-radius:cx+radius] = bumped
# save results
cv2.imwrite("portrait_of_mussorgsky2_bump.jpg", result)
# display images
cv2.imshow('img', img)
cv2.imshow('crop', crop)
cv2.imshow('bump', bump)
cv2.imshow('mask', mask)
cv2.imshow('bumped', bumped)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Resulting Image:

I think you need "Bulge" effects such as implode and explode. There are no implementation of these filters in OpenCV but, you can find other tools such as Wand(a python binding for ImageMagick) that have implode/explode.
Example (wand):
from wand.image import Image
with Image(filename="test.jpg") as img:
img.implode(amount = -0.2)
img.save(filename="destination.jpg")
# img_array = numpy.asarray(img) --> you can convert wand.image.Image to numpy array for further uses
passing negative values into implode functions is equal to doing explode. So for magnifying effect use negative values.
There is one problem though: img.implode performs on the center of the image, so after you've found the face features(eye, nose, ...) you need to move your picture somehow to make the eye or nose to lie on the center of the image. After that you can simply use implode function.

How to warp an document image in python correctly?

By using this link, I made the deformed mesh:
inputs = cv2.imread("../datasets/images/0.jpg")
nh, nw = inputs.shape[0]//8, inputs.shape[1]//8
inputs = cv2.resize(inputs, dsize=(nh, nw), interpolation=cv2.INTER_AREA)
mr = nh
mc = nw
xx = np.arange(mr-1, -1, -1)
yy = np.arange(0, mc, 1)
[Y, X] = np.meshgrid(xx, yy)
ms = np.transpose(np.asarray([X.flatten('F'), Y.flatten('F')]), (1,0))
perturbed_mesh = ms
nv = np.random.randint(20) - 1
for k in range(nv):
#Choosing one vertex randomly
vidx = np.random.randint(np.shape(ms)[0])
vtex = ms[vidx, :]
#Vector between all vertices and the selected one
xv = perturbed_mesh - vtex
#Random movement
mv = (np.random.rand(1,2) - 0.5)*20
hxv = np.zeros((np.shape(xv)[0], np.shape(xv)[1] +1) )
hxv[:, :-1] = xv
hmv = np.tile(np.append(mv, 0), (np.shape(xv)[0],1))
d = np.cross(hxv, hmv)
d = np.absolute(d[:, 2])
d = d / (np.linalg.norm(mv, ord=2))
wt = d
curve_type = np.random.rand(1)
if curve_type > 0.3:
alpha = np.random.rand(1) * 50 + 50
wt = alpha / (wt + alpha)
else:
alpha = np.random.rand(1) + 1
wt = 1 - (wt / 100 )**alpha
msmv = mv * np.expand_dims(wt, axis=1)
perturbed_mesh = perturbed_mesh + msmv
So I got the mesh like:
Then I tried to map the source image pixels onto the generated mesh.
img = cv2.copyMakeBorder(inputs, dh, dh, dw, dw, borderType=cv2.BORDER_CONSTANT, value=(0,0,0))
xs, ys = perturbed_mesh[:, 0], perturbed_mesh[:, 1]
xs = xs.reshape(nh, nw).astype(np.float32)
ys = ys.reshape(nh, nw).astype(np.float32)
dst = cv2.remap(img, xs, ys, cv2.INTER_CUBIC)
plt.imshow(dst)
Finally, I got the result:
But this image have a document on the corner, I can't use it.
How to map the document onto the center of image?

Here is an example of what I did for a perspective warp in Python/OpenCV. It will show you how I achieved the expanded view of the output. Not only did I increase the output size, but I also shifted the output control points. I shifted by +500 px and doubled that to +1000 for the output size.
Input:
No Expand Case:
import numpy as np
import cv2
# read input
img = cv2.imread("building.jpg")
# resize
height,width = 1000,1500
img = cv2.resize(img, (width,height))
# specify conjugate coordinates and shift output on left and top
pts1 = np.float32([[ 250, 0],[1220, 300],[1300, 770],[ 250, 860]])
pts2 = np.float32([[0,0],[width,0],[width,height],[0,height]])
# compute perspective matrix
matrix = cv2.getPerspectiveTransform(pts1,pts2)
print(matrix.shape)
print(matrix)
# convert image to BGRA with opaque alpha
img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
# do perspective transformation setting area outside input to transparent
# extend output size so extended by 500 all around
imgOutput = cv2.warpPerspective(img, matrix, (width,height), cv2.INTER_LINEAR, borderMode=cv2.BORDER_CONSTANT, borderValue=(0,0,0))
# resize output, since it is too large to post
imgOutput = cv2.resize(imgOutput, (width,height))
# save the warped output
cv2.imwrite("building_warped_unexpanded.png", imgOutput)
# show the result
cv2.imshow("result", imgOutput)
cv2.waitKey(0)
cv2.destroyAllWindows()
No Expand Warped Result:
Expanded Case:
import numpy as np
import cv2
# read input
img = cv2.imread("building.jpg")
# resize
height,width = 1000,1500
img = cv2.resize(img, (width,height))
# specify conjugate coordinates and shift output on left and top
pts1 = np.float32([[ 250, 0],[1220, 300],[1300, 770],[ 250, 860]])
pts2 = np.float32([[+500,+500],[width+500,+500],[width+500,height+500],[+500,height+500]])
# compute perspective matrix
matrix = cv2.getPerspectiveTransform(pts1,pts2)
print(matrix.shape)
print(matrix)
# convert image to BGRA with opaque alpha
img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
# do perspective transformation setting area outside input to transparent
# extend output size so extended by 500 all around
imgOutput = cv2.warpPerspective(img, matrix, (width+1000,height+1000), cv2.INTER_LINEAR, borderMode=cv2.BORDER_CONSTANT, borderValue=(0,0,0))
# resize output, since it is too large to post
imgOutput = cv2.resize(imgOutput, (width,height))
# save the warped output
cv2.imwrite("building_warped.jpg", imgOutput)
# show the result
cv2.imshow("result", imgOutput)
cv2.waitKey(0)
cv2.destroyAllWindows()
Expanded Result: