Develop Reference

Correct the object orientation in the image. Calculate the correct angle of rotation and correct the alignment of the object in the image

I have cropped images of electronic meter reading. Those readings are taken in random style. I need the orientation of the object(not the image) in the image to be aligned.
The detection of contours is not working. As there are lots of contours are formed in the image and in order to calculate the angle I need to select the right contour. Some times contour is not formed.
2.I want set of rotated images as shown in figure above. I tried some code of rotating image from the OpenCV. But due to two type of use case ( as we don't know from code that the reading style may be any of the two) The images are turned out as below.
Using the code below I am able to find the angle of rotation but for any one case. I need it to be done automatically for both type of cases. Also see the data set I have attached for other type of examples.
import cv2
import numpy as np
debug = True
# Display image
def display(img, frameName="OpenCV Image"):
if not debug:
return
h, w = img.shape[0:2]
neww = 800
newh = int(neww*(h/w))
img = cv2.resize(img, (neww, newh))
plt.imshow(img)
plt.show()
# cv2.imshow(frameName, img)
# cv2.waitKey(0)
#rotate the image with given theta value
def rotate(img, theta):
rows, cols = img.shape[0], img.shape[1]
image_center = (cols/2, rows/2)
M = cv2.getRotationMatrix2D(image_center,theta,1)
abs_cos = abs(M[0,0])
abs_sin = abs(M[0,1])
bound_w = int(rows * abs_sin + cols * abs_cos)
bound_h = int(rows * abs_cos + cols * abs_sin)
M[0, 2] += bound_w/2 - image_center[0]
M[1, 2] += bound_h/2 - image_center[1]
# rotate orignal image to show transformation
rotated = cv2.warpAffine(img,M,(bound_w,bound_h),borderValue=(255,255,255))
return rotated
def slope(x1, y1, x2, y2):
if x1 == x2:
return 0
slope = (y2-y1)/(x2-x1)
theta = np.rad2deg(np.arctan(slope))
return theta
def main(filePath):
img = cv2.imread(filePath)
(hi, wi) = img.shape[:2]
textImg = img.copy()
small = cv2.cvtColor(textImg, cv2.COLOR_BGR2GRAY)
# find the gradient map
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
grad = cv2.morphologyEx(small, cv2.MORPH_GRADIENT, kernel)
display(grad)
# Binarize the gradient image
_, bw = cv2.threshold(grad, 0.0, 255.0, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
display(bw)
# connect horizontally oriented regions
# kernal value (9,1) can be changed to improved the text detection
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 1))
connected = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)
display(connected)
# using RETR_EXTERNAL instead of RETR_CCOMP
# _ , contours, hierarchy = cv2.findContours(connected.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
contours, hierarchy = cv2.findContours(connected.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) #opencv >= 4.0
mask = np.zeros(bw.shape, dtype=np.uint8)
display(mask)
# cumulative theta value
cummTheta = 0
# number of detected text regions
ct = 0
flag=False
for idx in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[idx])
mask[y:y+h, x:x+w] = 0
# fill the contour
cv2.drawContours(mask, contours, idx, (255, 255, 255), -1)
display(mask)
# ratio of non-zero pixels in the filled region
r = float(cv2.countNonZero(mask[y:y+h, x:x+w])) / (w * h)
# assume at least 45% of the area is filled if it contains text
# if r > 0.39 and w > 8 and h > 8:
if (h/hi)>0.4 and (w/wi)>0.4:
flag=True
print(r,w,h)
# cv2.rectangle(textImg, (x1, y), (x+w-1, y+h-1), (0, 255, 0), 2)
rect = cv2.minAreaRect(contours[idx])
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(textImg,[box],0,(0,0,255),2)
center = (int(rect[0][0]),int(rect[0][1]))
width = int(rect[1][0])
height = int(rect[1][1])
angle = int(rect[2])
print(angle)
print(width,height)
if width < height:
angle = 90+angle
print(angle,'final')
# we can filter theta as outlier based on other theta values
# this will help in excluding the rare text region with different orientation from ususla value
theta = slope(box[0][0], box[0][1], box[1][0], box[1][1])
cummTheta += theta
ct +=1
# print("Theta", theta)
# find the average of all cumulative theta value
# orientation = cummTheta/ct
print("Image orientation in degress: ", angle)
finalImage = rotate(img, angle)
display(textImg, "Detectd Text minimum bounding box")
display(finalImage)
out_path='cropped_corrected/rotated/'+filePath.split('\\')[-1]
print(out_path)
cv2.imwrite(out_path,finalImage)
print('image svaed here in rotated')
break
if not flag:
out_path='cropped_corrected/not_rotated/'+filePath.split('\\')[-1]
print(out_path)
cv2.imwrite(out_path,img)
print('image svaed here without rotated')
if __name__ == "__main__":
filePath = 'cropped/N3963001963.jpg'
main(filePath)
I am attaching some sample images that need to be rotated and the object inside the image needs to be aligned:

How to vectorize an image using OpenCV?

I'm using the term "vectorize" because that is what has been used to describe the process I'm writing about. I don't know what it's actually called, but what I'm trying to do is take the elements of an image and separate them into different images.
Here is an example picture I'm trying to "vectorize":
What I would like to do is (using OpenCV) separate the corncob from the green stock it's attached to, and separate each corncob chunk into its own images.
What I have tried is the following:
def kmeansSegmentation(path_to_images, image_name, path_to_save_segments):
img = cv2.imread(path_to_images+image_name)
img_blur = cv2.GaussianBlur(img, (3,3), 0)
img_gray = cv2.cvtColor(img_blur, cv2.COLOR_BGR2GRAY)
img_reshaped = img_gray.reshape((-1, 3))
img_reshaped = np.float32(img_reshaped)
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
K = 5
attempts = 10
ret,label,center=cv2.kmeans(img_reshaped,K,None,criteria,attempts,cv2.KMEANS_PP_CENTERS)
center = np.uint8(center)
res = center[label.flatten()]
v = np.median(res)
sigma=0.33
lower = int(max(0, (1.0 - sigma) * v))
upper = int(min(255, (1.0 + sigma) * v))
edges = cv2.Canny(img_gray, lower, upper)
contours, hierarchy = cv2.findContours(edges.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
sorted_contours= sorted(contours, key=cv2.contourArea, reverse= True)
mask = np.zeros(img.shape[:2], dtype=img.dtype)
array_of_contour_areas = [cv2.contourArea(contour) for contour in contours]
contour_avg = sum(array_of_contour_areas)/len(array_of_contour_areas)
contour_var = sum(pow(x-contour_avg,2) for x in array_of_contour_areas) / len(array_of_contour_areas)
contour_std = math.sqrt(contour_var)
print("Saving segments", len(sorted_contours))
for (i,c) in tqdm(enumerate(sorted_contours)):
if (cv2.contourArea(c) > contour_avg-contour_std*2):
x,y,w,h= cv2.boundingRect(c)
cropped_contour= img[y:y+h, x:x+w]
cv2.drawContours(mask, [c], 0, (255), -1)
#tmp_image_name= image_name + "-kmeans-" + str(K) + str(random.random()) + ".jpg"
#cv2.imwrite(path_to_save_segments+tmp_image_name, cropped_contour)
result = cv2.bitwise_and(img, img, mask=mask)
"""
scale_percent = 30 # percent of original size
width = int(edges.shape[1] * scale_percent / 100)
height = int(edges.shape[0] * scale_percent / 100)
dim = (width, height)
resized = cv2.resize(result, dim, interpolation = cv2.INTER_AREA)
cv2.imshow("edges", resized)
cv2.waitKey(0)
cv2.destroyAllWindows()
"""
#tmp_image_name= image_name + "-kmeans-" + str(K) + str(random.random()) + ".png"
#cv2.imwrite(path_to_save_segments+tmp_image_name, result)
return result
Excuse the commented out code; that's me just observing the changes I make to the image as I modify the algorithm.

I believe what you are trying to do is something called "Instance Segmentation". This process is best done with deep learning techniques which might not suit you unless you can find a pre-trained model. Here is an article on how you can do that: https://www.analyticsvidhya.com/blog/2019/04/introduction-image-segmentation-techniques-python/
A more simple (but way less accurate) solution might be to just find use RGB threshold values to create an "outline" of the picture and then use a flood fill algorithm to discern specific pixels in the resulting image. To make a rough outline of the image, you'll have to experiment with different threshold values. First, convert the whole image to grayscale w. OpenCV (cv2.imread('image-name', 0)). To test different threshold values, simply check if each pixel value is above or below a certain value (that you pick):
import numpy as np
import cv2
import matplotlib.pyplot as plt
def apply_threshold(img_array, threshold):
threshold_applied = []
for row in img_array:
threshold_applied.append([])
for pixel in row:
if pixel>threshold:
threshold_applied[len(threshold_applied)-1].append([255, 255, 255])
else:
threshold_applied[len(threshold_applied)-1].append([0, 0, 0])
new_img = np.array(threshold_applied, np.uint8)
cv2.imwrite(str(threshold)+".jpg", new_img)
img = cv2.imread("Ek1Dx.jpg", 0)
apply_threshold(img, 210)
If you run the code, you can see that the output is extremely inaccurate and that the cob and the kernels of corn are barely visible. Instance segmentation and dividing images has actually been a very big computer science problem for the past decade or so. There may be other filters you can use to get more accurate results, but I think identifying a threshold is a baseline image segmentation technique. If you want, you can try tweaking around with the threshold value in the program to see if it'll get you a more divided image.

How can I find the center the hole with hough circles

For this image, I tried to use hough cirlce to find the center of the "black hole".
After playing with the parameters of cv2.HoughCircles for a long time, the following is the best I can get.
raw image:
# reproducible code for stackoverflow
import cv2
import os
import sys
from matplotlib import pyplot as plt
import numpy as np
# read image can turn it gray
img = cv2.imread(FILE)
cimg = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img_gray = dst = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
plt.figure(figsize = (18,18))
plt.imshow(cimg, cmap = "gray")
# removing noises
element = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
closing = cv2.morphologyEx(y, cv2.MORPH_CLOSE, element, iterations = 7)
plt.figure(figsize = (12,12))
plt.imshow(closing, cmap = "gray")
# try to find the circles
circles = cv2.HoughCircles(closing,cv2.HOUGH_GRADIENT,3,50,
param1=50,param2=30,minRadius=20,maxRadius=50)
circles = np.uint16(np.around(circles))
for i in circles[0,:]:
# draw the outer circle
cv2.circle(cimg,(i[0],i[1]),i[2],(0,255,0),2)
# draw the center of the circle
cv2.circle(cimg,(i[0],i[1]),2,(0,0,255),3)
plt.figure(figsize = (12,12))
plt.imshow(cimg)
Update::
The one with Canny:
edges = cv2.Canny(closing, 100, 300)
plt.figure(figsize = (12,12))
plt.imshow(edges, cmap = "gray")
circles = cv2.HoughCircles(edges,cv2.HOUGH_GRADIENT,2,50,
param1=50,param2=30,minRadius=20,maxRadius=60)
circles = np.uint16(np.around(circles))
cimg = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
for i in circles[0,:]:
# draw the outer circle
cv2.circle(cimg,(i[0],i[1]),i[2],(0,255,0),2)
# draw the center of the circle
cv2.circle(cimg,(i[0],i[1]),2,(0,0,255),3)
plt.figure(figsize = (12,12))
plt.imshow(cimg)
Still not the right circle that is wanted.
Update:
#crackanddie
Sometimes there is 6 or 9 in the identity number.
The circle in 6 or 9 is not very round.
Is there any way to filter that out?

This is an alternative method if you do not want to implement or fiddle with Hough's parameters. You must be sure there's at least one circle visible in your picture. The idea is to create a segmentation mask based on the CMYK color space and filter the blobs of interest by circularity and area. These are the steps:
Convert the image from BGR to CMYK
Threshold the K channel to get a binary mask
Filter blobs by circularity and area
Approximate the filtered blobs as circles
I'm choosing the CMYK color space because the circle is mostly black. The K (key) channel (in this case - black) should do a good job of representing the blob of interest, albeit, with some noise - as usual. Let's see the code:
# Imports:
import cv2
import numpy as np
# image path
path = "D://opencvImages//"
fileName = "dyj3O.jpg"
# load image
bgr = cv2.imread(path + fileName)
Alright, we need to convert the image from BGR to CMYK. OpenCV does not offer the conversion, so we need to do it manually. The formula is very straightforward. I'm just interested on the K channel, so I just calculate it like this:
# Make float and divide by 255:
bgrFloat = bgr.astype(np.float) / 255.
# Calculate K as (1 - whatever is biggest out of bgrFloat)
kChannel = 1 - np.max(bgrFloat, axis=2)
# Convert back to uint 8:
kChannel = 255 * kChannel
kChannel = kChannel.astype(np.uint8)
Gotta keep en eye on the data types, because there are float operations going on. This is the result:
As you see, the hole is almost 100% white, that's cool, we can threshold this image via Otsu like this:
# Compute binary mask of the hole via Otsu:
_, binaryImage = cv2.threshold(kChannel, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
Which gives you this nice binary mask:
Now, here comes the laborious part. Let's find contours on this image. For every contour/blob compute circularity and area. Use this info to filter noise and get the contour of interest, keep in mind that a perfect circle should have circularity close to 1.0. Once you get a contour of interest, approximate a circle to it. This is the process:
# Find the big contours/blobs on the filtered image:
contours, hierarchy = cv2.findContours(binaryImage, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
# Store the detected circles here:
detectedCircles = []
# Look for the potential contours of interest:
for _, c in enumerate(contours):
# Get the blob's area and perimeter:
contourArea = cv2.contourArea(c)
contourPerimeter = cv2.arcLength(c, True)
# Compute circularity:
if contourPerimeter > 0:
circularity = (4 * 3.1416 * contourArea) / (pow(contourPerimeter, 2))
else:
circularity = 0.0
# Set the min threshold values to identify the
# blob of interest:
minCircularity = 0.7
minArea = 2000
if circularity >= minCircularity and contourArea >= minArea:
# Approximate the contour to a circle:
(x, y), radius = cv2.minEnclosingCircle(c)
# Compute the center and radius:
center = (int(x), int(y))
# Cast radius to in:
radius = int(radius)
# Store the center and radius:
detectedCircles.append([center, radius])
# Draw the circles:
cv2.circle(bgr, center, radius, (0, 255, 0), 2)
cv2.imshow("Detected Circles", bgr)
print("Circles Found: " + str(len(detectedCircles)))
Additionally, I have stored the circle (center and radius) in the detectedCircles list. This is the final result:
Circles Found: 1

Here it is:
import numpy as np
import cv2
def threshold_gray_const(image_, rang: tuple):
return cv2.inRange(image_, rang[0], rang[1])
def binary_or(image_1, image_2):
return cv2.bitwise_or(image_1, image_2)
def negate_image(image_):
return cv2.bitwise_not(image_)
def particle_filter(image_, power):
# Abdrakov's particle filter
nb_components, output, stats, centroids = cv2.connectedComponentsWithStats(image_, connectivity=8)
sizes = stats[1:, -1]
nb_components = nb_components - 1
min_size = power
img2 = np.zeros(output.shape, dtype=np.uint8)
for i in range(0, nb_components):
if sizes[i] >= min_size:
img_to_compare = threshold_gray_const(output, (i + 1, i + 1))
img2 = binary_or(img2, img_to_compare)
img2 = img2.astype(np.uint8)
return img2
def reject_borders(image_):
# Abdrakov's border rejecter
out_image = image_.copy()
h, w = image_.shape[:2]
for row in range(h):
if out_image[row, 0] == 255:
cv2.floodFill(out_image, None, (0, row), 0)
if out_image[row, w - 1] == 255:
cv2.floodFill(out_image, None, (w - 1, row), 0)
for col in range(w):
if out_image[0, col] == 255:
cv2.floodFill(out_image, None, (col, 0), 0)
if out_image[h - 1, col] == 255:
cv2.floodFill(out_image, None, (col, h - 1), 0)
return out_image
src = cv2.imread("your_image")
img_gray = dst = cv2.cvtColor(src, cv2.COLOR_BGR2GRAY)
element = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
closing = cv2.morphologyEx(img_gray, cv2.MORPH_CLOSE, element, iterations=2)
tv, thresh = cv2.threshold(closing, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
neg = negate_image(thresh)
rej = reject_borders(neg)
filtered = particle_filter(rej, 300)
edges = cv2.Canny(filtered, 100, 200)
circles = cv2.HoughCircles(edges, cv2.HOUGH_GRADIENT, 3, 50, param1=50, param2=30, minRadius=20, maxRadius=50)
circles = np.uint16(np.around(circles))
for i in circles[0, :]:
# draw the outer circle
cv2.circle(src, (i[0], i[1]), i[2], (0, 255, 0), 2)
# draw the center of the circle
cv2.circle(src, (i[0], i[1]), 2, (0, 0, 255), 3)
cv2.imshow("closing", closing)
cv2.imshow("edges", edges)
cv2.imshow("out", src)
cv2.waitKey(0)
I changed cv2.morphologyEx parameters a bit, because they were too strong. And after this noise removing I made a binary image using cv2.THRESH_OTSU parameter, negated it, rejected borders and filtered a bit. Then I used cv2.Canny to find edges and this 'cannied' image I passed into cv2.HoughCircles. If any questions - ask me :)

If you want to use a "thinking out of the box" solution then check this solution out. Remember this might have a few false positives in some cases and would only work in cases where circle contour is complete or joined.
import numpy as np
import cv2
import matplotlib.pyplot as plt
from math import pi
pi_eps = 0.1
rgb = cv2.imread('/path/to/your/image/find_circle.jpg')
gray = cv2.cvtColor(rgb, cv2.COLOR_BGR2GRAY)
th = cv2.adaptiveThreshold(gray,255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY_INV,21,5)
contours, hier = cv2.findContours(th.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
out_img = rgb.copy()
for i in range(len(contours)):
x,y,w,h = cv2.boundingRect(contours[i])
ar = min(w,h)/max(w,h)
# For a circle aspect ratio is close to 1.0
# In your use case circle diameter is between 40px-100px
if ar < 0.9 or \
w < 40 or w > 100:
continue
# P = 2 * PI * r
perimeter = cv2.arcLength(contours[i], True)
if perimeter == 0:
continue
# Second level confirmation could be done using PI = P * P / (4 * A)
# A = PI * r * r
area = cv2.contourArea(contours[i])
if area == 0:
continue
# d = (w+h) / 2 average diameter
# A contour is a circle if (P / d) = PI
ctr_pi = perimeter / ((w+h) / 2)
if abs(ctr_pi - pi) < pi_eps * pi:
cv2.circle(out_img, (int(x+w/2), int(y+h/2)), int(max(w,h)/2), (0, 255, 0), 1)
print("Center of the circle: ", x + w/2, y+h/2)
plt.imshow(out_img)

Corner detection with Hughlines transformation

I need to detect corner of a paper on given image. It will always be a cropped part of whole picture containing only one of the corners. My idea was to transform image by bluring and Canny edge detection to get outlines and then aplying Houghlines to get coordinates of corner.
However i get some problem to actualy detect anything consistently and precisly by Hough lines and I'm running out of ideas what can be the cause here.
I've tried tresholding instead of Canny, but it's not gonna work due to many variations in applicable images. I've downcaled whole image to make it easier to see just edges of paper, but still no improvement. Increasing line tresholds make lines from paper content diapear, but at the same time edge lines disapear from time to time
Input
Edges
Results
Code to reproduce
import cv2
import numpy as np
img = cv2.imread('inv_0001-01.1_0_corner.jpg')
resized = cv2.resize(img, (250,250), interpolation = cv2.INTER_AREA)
gray = cv2.cvtColor(resized, cv2.COLOR_BGR2GRAY)
kernel_size = 5
blur_gray = cv2.GaussianBlur(gray,(kernel_size, kernel_size),0)
edges = cv2.Canny(blur_gray,50,150,apertureSize = 3)
cv2.imshow('edges', edges)
cv2.waitKey()
min_line_length = 50
max_line_gap = 20
lines = cv2.HoughLinesP(edges, 1, np.pi / 180, 5, np.array([]), min_line_length, max_line_gap)
for line in lines:
for x1,y1,x2,y2 in line:
cv2.line(resized,(x1,y1),(x2,y2),(255,0,0),5)
cv2.imshow('hough', resized)
cv2.waitKey()
My go-to result would be coordinate of paper corner in given image, but in this post I'm rather looking for some help in understanding how to use Houglines for such tasks

This answer explains how to find the corner. Finding the corner requires a two part solution. First, the image needs to be segmented in to two regions: paper and background. Second, you can look for corners in the segmented image.
After you find the edges, floodfill the image to segment the paper from the background (this is the floodfill image):
mask = np.zeros((h+2, w+2), np.uint8)
# Floodfill from point (0, 0)
cv2.floodFill(edges, mask, (0,0), 123);
Now that you have segmented the image, get rid of the text on the paper using a mask (this is the image titled 'Masking'):
bg = np.zeros_like(edges)
bg[edges == 123] = 255
After you get the mask, appl the canny edge filter again to get the out line of the paper (HoughLines needs an outline not a mask...this is the 'Edges after masking' image):
bg = cv2.blur(bg, (3,3))
edges = cv2.Canny(bg,50,150,apertureSize = 3)
Now you can run your HoughLines algorithm on the cleaner image. I used a different HoughLines algorithm than you did, but yours should work too. Here is the full code that I used:
import cv2
import numpy as np
import matplotlib.pyplot as plt
# Create a multi plot
f, axarr = plt.subplots(2,3, sharex=True)
img = cv2.imread('/home/stephen/Desktop/IRcCAWL.png')
resized = cv2.resize(img, (250,250), interpolation = cv2.INTER_AREA)
# Show source image
axarr[0,0].imshow(resized)
gray = cv2.cvtColor(resized, cv2.COLOR_BGR2GRAY)
kernel_size = 5
blur_gray = cv2.GaussianBlur(gray,(kernel_size, kernel_size),0)
edges = cv2.Canny(blur_gray,50,150,apertureSize = 3)
# Show first edges image
axarr[0,1].imshow(edges)
h, w = edges.shape[:2]
mask = np.zeros((h+2, w+2), np.uint8)
# Floodfill from point (0, 0)
cv2.floodFill(edges, mask, (0,0), 123);
# Show the flood fill image
axarr[0,2].imshow(edges)
floodfill = edges.copy()
bg = np.zeros_like(edges)
bg[edges == 123] = 255
# Show the masked image
axarr[1,0].imshow(bg)
bg = cv2.blur(bg, (3,3))
edges = cv2.Canny(bg,50,150,apertureSize = 3)
# Show the edges after masking
axarr[1,1].imshow(edges)
min_line_length = 50
max_line_gap = 20
def intersection(line1, line2):
"""Finds the intersection of two lines given in Hesse normal form.
Returns closest integer pixel locations.
See https://stackoverflow.com/a/383527/5087436
"""
rho1, theta1 = line1[0]
rho2, theta2 = line2[0]
A = np.array([
[np.cos(theta1), np.sin(theta1)],
[np.cos(theta2), np.sin(theta2)]
])
b = np.array([[rho1], [rho2]])
x0, y0 = np.linalg.solve(A, b)
x0, y0 = int(np.round(x0)), int(np.round(y0))
return [[x0, y0]]
import math
lines = cv2.HoughLines(edges, 1, np.pi / 180, 100, None, 0, 0)
# Draw the lines
if lines is not None:
for i in range(0, len(lines)):
rho = lines[i][0][0]
theta = lines[i][0][1]
a = math.cos(theta)
b = math.sin(theta)
x0 = a * rho
y0 = b * rho
pt1 = (int(x0 + 1000*(-b)), int(y0 + 1000*(a)))
pt2 = (int(x0 - 1000*(-b)), int(y0 - 1000*(a)))
cv2.line(resized, pt1, pt2, (123,234,123), 2, cv2.LINE_AA)
xy = tuple(intersection(lines[0], lines[1])[0])
resized = cv2.circle(resized, xy, 5, 255, 2)
# Show the image with the corner
axarr[1,2].imshow(resized)
# Add titles
axarr[0,0].set_title('Source Image')
axarr[0,1].set_title('Edges')
axarr[0,2].set_title('Floodfill')
axarr[1,0].set_title('Masking')
axarr[1,1].set_title('Edges after masking')
axarr[1,2].set_title('Hough Lines')
# Clean up
axarr[0,0].axis('off')
axarr[0,1].axis('off')
axarr[1,0].axis('off')
axarr[1,1].axis('off')
axarr[1,2].axis('off')
axarr[0,2].axis('off')
plt.show()

Blend overlapping images in python

I am taking two images in python and overlapping the first image onto the second image. What I would like to do is blend the images where they overlap. Is there a way to do this in python other than a for loop?

PIL has a blend function which combines two RGB images with a fixed alpha:
out = image1 * (1.0 - alpha) + image2 * alpha
However, to use blend, image1 and image2 must be the same size.
So to prepare your images you'll need to paste each of them into a new image of
the appropriate (combined) size.
Since blending with alpha=0.5 averages the RGB values from both images equally,
we need to make two versions of the panorama -- one with img1 one top and one with img2 on top. Then regions with no overlap have RGB values which agree (so their averages will remain unchanged) and regions of overlap will get blended as desired.
import operator
from PIL import Image
from PIL import ImageDraw
# suppose img1 and img2 are your two images
img1 = Image.new('RGB', size=(100, 100), color=(255, 0, 0))
img2 = Image.new('RGB', size=(120, 130), color=(0, 255, 0))
# suppose img2 is to be shifted by `shift` amount
shift = (50, 60)
# compute the size of the panorama
nw, nh = map(max, map(operator.add, img2.size, shift), img1.size)
# paste img1 on top of img2
newimg1 = Image.new('RGBA', size=(nw, nh), color=(0, 0, 0, 0))
newimg1.paste(img2, shift)
newimg1.paste(img1, (0, 0))
# paste img2 on top of img1
newimg2 = Image.new('RGBA', size=(nw, nh), color=(0, 0, 0, 0))
newimg2.paste(img1, (0, 0))
newimg2.paste(img2, shift)
# blend with alpha=0.5
result = Image.blend(newimg1, newimg2, alpha=0.5)
img1:
img2:
result:
If you have two RGBA images here is a way to perform alpha compositing.

If you'd like a soft edge when stitching two images together you could blend them with a sigmoid function.
Here is a simple grayscale example:
import numpy as np
import matplotlib.image
import math
def sigmoid(x):
y = np.zeros(len(x))
for i in range(len(x)):
y[i] = 1 / (1 + math.exp(-x[i]))
return y
sigmoid_ = sigmoid(np.arange(-1, 1, 1/50))
alpha = np.repeat(sigmoid_.reshape((len(sigmoid_), 1)), repeats=100, axis=1)
image1_connect = np.ones((100, 100))
image2_connect = np.zeros((100, 100))
out = image1_connect * (1.0 - alpha) + image2_connect * alpha
matplotlib.image.imsave('blend.png', out, cmap = 'gray')
If you blend white and black squares result will look something like that:
+ =