Develop Reference

How to rotate an image to get not-null pixels?

In the image I linked below, I need to get all the yellow/green pixels in this rotated rectangle and get rid of the blue background, so that the rectangle's axis are aligned with the x and y axis.
I'm using numpy but don't have a clue what I should do.
I uploaded the array in this drive in case anyone would like to work with the actual array
Thanks for the help in advance.

I used the same image as user2640045, but different approach.
import numpy as np
import cv2
# load and convert image to grayscale
img = cv2.imread('image.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# binarize image
threshold, binarized_img = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# find the largest contour
contours, hierarchy = cv2.findContours(binarized_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
c = max(contours, key = cv2.contourArea)
# get size of the rotated rectangle
center, size, angle = cv2.minAreaRect(c)
# get size of the image
h, w, *_ = img.shape
# create a rotation matrix and rotate the image
M = cv2.getRotationMatrix2D(center, angle, 1.0)
rotated_img = cv2.warpAffine(img, M, (w, h))
# crop the image
pad_x = int((w - size[0]) / 2)
pad_y = int((h - size[1]) / 2)
cropped_img = rotated_img[pad_y : pad_y + int(size[1]), pad_x : pad_x + int(size[0]), :]
Result:

I realize there is a allow_pickle=False option in numpys load method but I didn't feel comfortable with unpickling/using data from the internet so I used the small image. After removing the coordinate system and stuff I had
I define two helper methods. One to later rotate the image taken from an other stack overflow thread. See link below. And one to get a mask being one at a specified color and zero otherwise.
import numpy as np
import matplotlib.pyplot as plt
import sympy
import cv2
import functools
color = arr[150,50]
def similar_to_boundary_color(arr, color=tuple(color)):
mask = functools.reduce(np.logical_and, [np.isclose(arr[:,:,i], color[i]) for i in range(4)])
return mask
#https://stackoverflow.com/a/9042907/2640045
def rotate_image(image, angle):
image_center = tuple(np.array(image.shape[1::-1]) / 2)
rot_mat = cv2.getRotationMatrix2D(image_center, angle, 1.0)
result = cv2.warpAffine(image, rot_mat, image.shape[1::-1], flags=cv2.INTER_LINEAR)
return result
Next I calculate the angle to rotate about. I do that by finding the lowest pixel at width 50 and 300. I picked those since they are far enough from the boundary to not be effected by missing corners etc..
i,j = np.where(~similar_to_boundary_color(arr))
slope = (max(i[j == 50])-max(i[j == 300]))/(50-300)
angle = np.arctan(slope)
arr = rotate_image(arr, np.rad2deg(angle))
plt.imshow(arr)
.
One way of doing the cropping is the following. You calculate the mid in height and width. Then you take two slices around the mid say 20 pixels in one direction and to until the mid in the other one. The biggest/smallest index where the pixel is white/background colored is a reasonable point to cut.
i,j = np.where(~(~similar_to_boundary_color(arr) & ~similar_to_boundary_color(arr, (0,0,0,0))))
imid, jmid = np.array(arr.shape)[:2]/2
imin = max(i[(i < imid) & (jmid - 10 < j) & (j < jmid + 10)])
imax = min(i[(i > imid) & (jmid - 10 < j) & (j < jmid + 10)])
jmax = min(j[(j > jmid) & (imid - 10 < i) & (i < imid + 10)])
jmin = max(j[(j < jmid) & (imid - 10 < i) & (i < imid + 10)])
arr = arr[imin:imax,jmin:jmax]
plt.imshow(arr)
and the result is:

Image object reflection

Hello I want to reflect an object in the image as in this image[enter image description here][1]
[1]: https://i.stack.imgur.com/N9J3I.jpg How can I get this kind of result?

It is possible that OpenCV does not have good solutions for this, take a closer look at Pillow.
from PIL import Image, ImageFilter
def drop_shadow(image, iterations=3, border=8, offset=(5,5), background_colour=0xffffff, shadow_colour=0x444444):
shadow_width = image.size[0] + abs(offset[0]) + 2 * border
shadow_height = image.size[1] + abs(offset[1]) + 2 * border
shadow = Image.new(image.mode, (shadow_width, shadow_height), background_colour)
shadow_left = border + max(offset[0], 0)
shadow_top = border + max(offset[1], 0)
shadow.paste(shadow_colour, [shadow_left, shadow_top, shadow_left + image.size[0], shadow_top + image.size[1]])
for i in range(iterations):
shadow = shadow.filter(ImageFilter.BLUR)
img_left = border - min(offset[0], 0)
img_top = border - min(offset[1], 0)
shadow.paste(image, (img_left, img_top))
return shadow
drop_shadow(Image.open('boobs.jpg')).save('shadowed_boobs.png')

Here is one way to do the reflection in Python/OpenCV.
One flips the image. Then makes a vertical ramp (gradient) image and puts that into the alpha channel of the flipped image. Then one concatenates the original and the flipped images.
Input:
import cv2
import numpy as np
# set top and bottom opacity percentages
top = 85
btm = 15
# load image
img = cv2.imread('bear2.png')
hh, ww = img.shape[:2]
# flip the input
flip = np.flip(img, axis=0)
# add opaque alpha channel to input
img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
# make vertical gradient that is bright at top and dark at bottom as alpha channel for the flipped image
gtop = 255*top//100
gbtm = 255*btm//100
grady = np.linspace(gbtm, gtop, hh, dtype=np.uint8)
gradx = np.linspace(1, 1, ww, dtype=np.uint8)
grad = np.outer(grady, gradx)
grad = np.flip(grad, axis=0)
# alternate method
#grad = np.linspace(0, 255, hh, dtype=np.uint8)
#grad = np.tile(grad, (ww,1))
#grad = np.transpose(grad)
#grad = np.flip(grad, axis=0)
# put the gradient into the alpha channel of the flipped image
flip = cv2.cvtColor(flip, cv2.COLOR_BGR2BGRA)
flip[:,:,3] = grad
# concatenate the original and the flipped versions
result = np.vstack((img, flip))
# save output
cv2.imwrite('bear2_vertical_gradient.png', grad)
cv2.imwrite('bear2_reflection.png', result)
# Display various images to see the steps
cv2.imshow('flip',flip)
cv2.imshow('grad',grad)
cv2.imshow('result',result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Ramped (Gradient) Image:
Result:

Finding an unfilled circle in an image of finite size using Python

Trying to find a circle in an image that has finite radius. Started off using 'HoughCircles' method from OpenCV as the parameters for it seemed very much related to my situation. But it is failing to find it. Looks like the image may need more pre-processing for it to find reliably. So, started off playing with different thresholds in opencv to no success. Here is an example of an image (note that the overall intensity of the image will vary, but the radius of the circle always remain the same ~45pixels)
Here is what I have tried so far
image = cv2.imread('image1.bmp', 0)
img_in = 255-image
mean_val = int(np.mean(img_in))
ret, img_thresh = cv2.threshold(img_in, thresh=mean_val-30, maxval=255, type=cv2.THRESH_TOZERO)
# detect circle
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.0, 100, minRadius=40, maxRadius=50)
If you look at the image, the circle is obvious, its a thin light gray circle in the center of the blob.
Any suggestions?
Edited to show expected result
The expected result should be like this, as you can see, the circle is very obvious for naked eye on the original image and is always of the same radius but not at the same location on the image. But there will be only one circle of this kind on any given image.
As of 8/20/2020, here is the code I am using to get the center and radii
from numpy import zeros as np_zeros,\
full as np_full
from cv2 import calcHist as cv2_calcHist,\
HoughCircles as cv2_HoughCircles,\
HOUGH_GRADIENT as cv2_HOUGH_GRADIENT
def getCenter(img_in, saturated, minradius, maxradius):
img_local = img_in[100:380,100:540,0]
res = np_full(3, -1)
# do some contrast enhancement
img_local = stretchHistogram(img_local, saturated)
circles = cv2_HoughCircles(img_local, cv2_HOUGH_GRADIENT, 1, 40, param1=70, param2=20,
minRadius=minradius,
maxRadius=maxradius)
if circles is not None: # found some circles
circles = sorted(circles[0], key=lambda x: x[2])
res[0] = circles[0][0]+100
res[1] = circles[0][1]+100
res[2] = circles[0][2]
return res #x,y,radii
def stretchHistogram(img_in, saturated=0.35, histMin=0.0, binSize=1.0):
img_local = img_in.copy()
img_out = img_in.copy()
min, max = getMinAndMax(img_local, saturated)
if max > min:
min = histMin+min * binSize
max = histMin+max * binSize
w, h = img_local.shape[::-1]
#create a new lut
lut = np_zeros(256)
max2 = 255
for i in range(0, 256):
if i <= min:
lut[i] = 0
elif i >= max:
lut[i] = max2
else:
lut[i] = (round)(((float)(i - min) / (max - min)) * max2)
#update image with new lut values
for i in range(0, h):
for j in range(0, w):
img_out[i, j] = lut[img_local[i, j]]
return img_out
def getMinAndMax(img_in, saturated):
img_local = img_in.copy()
hist = cv2_calcHist([img_local], [0], None, [256], [0, 256])
w, h = img_local.shape[::-1]
pixelCount = w * h
saturated = 0.5
threshold = (int)(pixelCount * saturated / 200.0)
found = False
count = 0
i = 0
while not found and i < 255:
count += hist[i]
found = count > threshold
i = i + 1
hmin = i
i = 255
count = 0
while not found and i > 0:
count += hist[i]
found = count > threshold
i = i - 1
hmax = i
return hmin, hmax
and calling the above function as
getCenter(img, 5.0, 55, 62)
But it is still very unreliable. Not sure why it is so hard to get to an algorithm that works reliably for something that is very obvious to a naked eye. Not sure why there is so much variation in the result from frame to frame even though there is no change between them.
Any suggestions are greatly appreciated. Here are some more samples to play with

simple, draw your circles: cv2.HoughCircles returns a list of circles..
take care of maxRadius = 100
for i in circles[0,:]:
# draw the outer circle
cv2.circle(image,(i[0],i[1]),i[2],(255,255,0),2)
# draw the center of the circle
cv2.circle(image,(i[0],i[1]),2,(255,0,255),3)
a full working code (you have to change your tresholds):
import cv2
import numpy as np
image = cv2.imread('0005.bmp', 0)
height, width = image.shape
print(image.shape)
img_in = 255-image
mean_val = int(np.mean(img_in))
blur = cv2.blur(img_in , (3,3))
ret, img_thresh = cv2.threshold(blur, thresh=100, maxval=255, type=cv2.THRESH_TOZERO)
# detect circle
circles = cv2.HoughCircles(img_thresh, cv2.HOUGH_GRADIENT,1,40,param1=70,param2=20,minRadius=60,maxRadius=0)
print(circles)
for i in circles[0,:]:
# check if center is in middle of picture
if(i[0] > width/2-30 and i[0] < width/2+30 \
and i[1] > height/2-30 and i[1] < height/2+30 ):
# draw the outer circle
cv2.circle(image,(i[0],i[1]),i[2],(255,255,0),2)
# draw the center of the circle
cv2.circle(image,(i[0],i[1]),2,(255,0,255),3)
cv2.imshow("image", image )
while True:
keyboard = cv2.waitKey(2320)
if keyboard == 27:
break
cv2.destroyAllWindows()
result:

Pixels intensity values between two lines

I have created an alghoritm that detects the edges of an extruded colagen casing and draws a centerline between these edges on an image. Casing with a centerline.
Here is my code:
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
img = cv2.imread("C:/Users/5.jpg", cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (1500, 1200))
#ROI
fromCenter = False
r = cv2.selectROI(img, fromCenter)
imCrop = img[int(r[1]):int(r[1]+r[3]), int(r[0]):int(r[0]+r[2])]
#Operations on an image
_,thresh = cv2.threshold(imCrop,100,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
kernel = np.ones((5,5),np.uint8)
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
blur = cv2.GaussianBlur(opening,(7,7),0)
edges = cv2.Canny(blur, 0,20)
#Edges localization, packing coords into a list
indices = np.where(edges != [0])
coordinates = list(zip(indices[1], indices[0]))
num = len(coordinates)
#Separating into top and bot edge
bot_cor = coordinates[:int(num/2)]
top_cor = coordinates[-int(num/2):]
#Converting to arrays, sorting
a, b = np.array(top_cor), np.array(bot_cor)
a, b = a[a[:,0].argsort()], b[b[:,0].argsort()]
#Edges approximation by a 5th degree polynomial
min_a_x, max_a_x = np.min(a[:,0]), np.max(a[:,0])
new_a_x = np.linspace(min_a_x, max_a_x, imCrop.shape[1])
a_coefs = np.polyfit(a[:,0],a[:,1], 5)
new_a_y = np.polyval(a_coefs, new_a_x)
min_b_x, max_b_x = np.min(b[:,0]), np.max(b[:,0])
new_b_x = np.linspace(min_b_x, max_b_x, imCrop.shape[1])
b_coefs = np.polyfit(b[:,0],b[:,1], 5)
new_b_y = np.polyval(b_coefs, new_b_x)
#Defining a centerline
midx = [np.average([new_a_x[i], new_b_x[i]], axis = 0) for i in range(imCrop.shape[1])]
midy = [np.average([new_a_y[i], new_b_y[i]], axis = 0) for i in range(imCrop.shape[1])]
plt.figure(figsize=(16,8))
plt.title('Cross section')
plt.xlabel('Length of the casing', fontsize=18)
plt.ylabel('Width of the casing', fontsize=18)
plt.plot(new_a_x, new_a_y,c='black')
plt.plot(new_b_x, new_b_y,c='black')
plt.plot(midx, midy, '-', c='blue')
plt.show()
#Converting coords type to a list (plotting purposes)
coords = list(zip(midx, midy))
points = list(np.int_(coords))
mask = np.zeros((imCrop.shape[:2]), np.uint8)
mask = edges
#Plotting
for point in points:
cv2.circle(mask, tuple(point), 1, (255,255,255), -1)
for point in points:
cv2.circle(imCrop, tuple(point), 1, (255,255,255), -1)
cv2.imshow('imCrop', imCrop)
cv2.imshow('mask', mask)
cv2.waitKey(0)
cv2.destroyAllWindows()
Now I would like to sum up the intensities of each pixel in a region between top edge and a centerline (same thing for a region between centerline and a bottom edge).
Is there any way to limit the ROI to the region between the detected edges and split it into two regions based on the calculated centerline?
Or is there any way to access the pixels which are contained between the edge and a centerline based on theirs coordinates?
(It's my very first post here, sorry in advance for all the mistakes)

I wrote a somewhat naïve code to get masks for the upper and lower part. My code considers that the source image will be always like yours: with horizontal stripes.
After applying Canny I get this:
Then I run some loops through image array to fill unwanted areas of your image. This is done separately for upper and lower part, creating masks. The results are:
Then you can use this masks to sum only the elements you're interested in, using cv.sumElems.
import cv2 as cv
#open as grayscale image
src = cv.imread("colagen.png",cv.IMREAD_GRAYSCALE)
# apply canny and find contours
threshold = 100
canny_output = cv.Canny(src, threshold, threshold * 2)
# find mask for upper part
mask1 = canny_output.copy()
x, y = canny_output.shape
area = 0
for j in range(y):
area = 0
for i in range(x):
if area == 0:
if mask1[i][j] > 0:
area = 1
continue
else:
mask1[i][j] = 255
elif area == 1:
if mask1[i][j] > 0:
area = 2
else:
continue
else:
mask1[i][j] = 255
mask1 = cv.bitwise_not(mask1)
# find mask for lower part
mask2 = canny_output.copy()
x, y = canny_output.shape
area = 0
for j in range(y):
area = 0
for i in range(x):
if area == 0:
if mask2[-i][j] > 0:
area = 1
continue
else:
mask2[-i][j] = 255
elif area == 1:
if mask2[-i][j] > 0:
area = 2
else:
continue
else:
mask2[-i][j] = 255
mask2 = cv.bitwise_not(mask2)
# apply masks and calculate sum of elements in upper and lower part
sums = [0,0]
(sums[0],_,_,_) = cv.sumElems(cv.bitwise_and(src,mask1))
(sums[1],_,_,_) = cv.sumElems(cv.bitwise_and(src,mask2))
cv.imshow('src',src)
cv.imshow('canny',canny_output)
cv.imshow('mask1',mask1)
cv.imshow('mask2',mask2)
cv.imshow('masked1',cv.bitwise_and(src,mask1))
cv.imshow('masked2',cv.bitwise_and(src,mask2))
cv.waitKey()
Alternatives...
Probably there exist some function that fill the areas of the Canny result. I tried cv.fillPoly and cv.floodFill, but didn't manage to make them work easily... But maybe someone else can help you with that...
Edit
Found another way to get the masks with a cleaner code. Using numpy np.add.accumulate then np.clip, and then a modulo operation:
# first divide canny_output by 255 to get 0's and 1's, then perform
# an accumulate addition for each column. Thus you'll get +1 for every
# line, "painting" areas with 1, 2, 3...
a = np.add.accumulate(canny_output/255,0)
# clip values: anything greater than 2 becomes 2
a = np.clip(a, 0, 2)
# performe a modulo, to get areas alternating with 0 or 1; then multiply by 255
a = a%2 * 255
# convert to uint8
mask1 = cv.convertScaleAbs(a)
# to get mask2 (the lower mask) flip the array then do the same as above
a = np.add.accumulate(np.flip(canny_output,0)/255,0)
a = np.clip(a, 0, 2)
a = a%2 * 255
mask2 = cv.convertScaleAbs(np.flip(a,0))
This returns almost the same result. The border of the mask is a little bit different...

OpenCV: augmenting video stream source .png not rendering transparency as expected

I am trying to create my own face filtering augmented reality program in open-cv. The idea is it will map a beaver to the users face. Currently, I am unable to get proper transperency when loading this image with 'cv2.imread(...)'. It looks black in the background, and often shows partially in certain areas that are white. When I open this image in photoshop, I am fully capable of moving this image on top of a background with expected transparency results. I am wondering if the alpha is not getting rendered properly. Here is the relevent code where I am loading the image in.
import numpy
import cv2
def augment_stream(face: numpy.array, augment: numpy.array) -> numpy.array:
face_h, face_w, _ = face.shape
augment_h, augment_w, _ = augment.shape
scalar = min(face_h / augment_h, face_w / augment_w)
delta_augment_h = int(scalar * augment_h)
delta_augment_w = int(scalar * augment_w)
delta_augment_shape = (delta_augment_w, delta_augment_h)
resized_augment = cv2.resize(augment, delta_augment_shape)
augmented_face = face.copy()
dark_pixels = (resized_augment < 250).all(axis=2)
offset_x = int((face_w - delta_augment_w) / 2)
offset_y = int((face_h - delta_augment_h) / 2)
augmented_face[offset_y: offset_y+delta_augment_h, offset_x: offset_x+delta_augment_w][dark_pixels] = resized_augment[dark_pixels]
return augmented_face
def main():
stream = cv2.VideoCapture(0)
cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
augment = cv2.imread('assets/normal.png')
# tmp = cv2.cvtColor(augment, cv2.COLOR_BGR2GRAY)
# _,alpha = cv2.threshold(tmp,0,255,cv2.THRESH_BINARY)
# b, g, r = cv2.split(augment)
# rgba = [b,g,r, alpha]
# dst = cv2.merge(rgba,4)
# cv2.imwrite("assets/normal.png", dst)
while True:
ret, border = stream.read()
border_h, border_w, _ = border.shape
bw = cv2.equalizeHist(cv2.cvtColor(border, cv2.COLOR_BGR2GRAY))
rects = cascade.detectMultiScale(bw, scaleFactor=1.3, minNeighbors=4, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE)
for x, y, w, h in rects:
y0 = int(y - 0.25*h)
y1 = int(y + 0.75*h)
x0 = x
x1 = x + w
if x0 < 0 or x1 > border_w or y0 < 0 or y1 > border_h:
continue
border[y0: y1, x0: x1] = augment_stream(border[y0: y1, x0: x1], augment)
cv2.imshow('border', border)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
stream.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
main()

Using example from question overlay a smaller image on a larger image python OpenCv
I reduced it to show only how to put image
use cv2.IMREAD_UNCHANGED to load it as RGBA.
split it to RGB and A
use A to create masks for image and border
use loop to add channels
import cv2
stream = cv2.VideoCapture(0)
# load RGBA
augment = cv2.imread('image.png', cv2.IMREAD_UNCHANGED) # load RGBA
# make it smaller then frame - only for test
W = 320
H = 240
augment = cv2.resize(augment, (W, H))
# split image and alpha
image = augment[:,:,0:3]
alpha = augment[:,:,3]
mask_image = alpha / 255.0
mask_border = 1.0 - mask_image
# ROI - region of interest
x1 = 200
y1 = 100
x2 = x1 + W
y2 = y1 + H
while True:
ret, border = stream.read()
# copy only in some region (ROI) (don't assign to variable) but gives worse result
#cv2.copyTo(image, alpha, border[y1:y2, x1:x2])
for c in range(0, 3): # channels RGB
border[y1:y2, x1:x2, c] = (image[:, :, c]*mask_image + border[y1:y2, x1:x2, c]*mask_border)
cv2.imshow('border', border)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
stream.release()
cv2.destroyAllWindows()
BTW: I tried to use cv2.copyTo(image, mask_image, border) but it gives worse result - maybe mask/alpha needs 3 channels.
It seems it can be done in C/C++ - how to insert a small size image on to a big image