Related
I'm trying to extract the corner points of a rectangular section containing bubbles from an OMR sheet so I can later use those points to warpPerspective to get bird's eye view on that section but I am not getting expected results.
Following is the OMR sheet image :- OMRsheet.jpg
Code :-
import cv2
import numpy as np
def extract_rect(contours): #Function to extract rectangular contours above a certain area unit
rect_contours = []
for c in contours:
if cv2.contourArea(c) > 10000:
perimeter = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02*perimeter, True) #approximates a curve or a polygon with another curve/polygon with less vertices so that the distance between them is less or equal to the specified precision. Uses Douglas-Peucker algorithm
if len(approx) == 4:
rect_contours.append(c)
rect_contours = sorted(rect_contours, key=cv2.contourArea,reverse=True) # Sorting the contours based on area from large to small
return rect_contours
def rect_points(rect_contour): #Function to find corner points of the contour passed #Something wrong with this Not giving expected results. Messing up the warping of the image
perimeter = cv2.arcLength(rect_contour, True)
approx = cv2.approxPolyDP(rect_contour, 0.02*perimeter, True)
print("APPROX")
print(type(approx))
print(approx)
cv2.drawContours(img, approx, -1, (100,10,55), 18) #Rechecking if cotour passed to this function is the correct one
cv2.drawContours(img, rect_contour, -1, (100,10,55), 1)
x, y, w, h = cv2.boundingRect(rect_contour) #I Suspect Logical error in this line as it returns corner points for the outer rectangle instead of the contour passed to it
print("printing x y w h")
print(x, y, w, h)
# Corner points of the rectangle further used to be used to warp the rectangular section
point_1 = np.array([x, y])
point_2 = np.array([x+w, y])
point_3 = np.array([x, y+h])
point_4 = np.array([w, h])
corner_list = np.ndarray(shape=(4,2), dtype=np.int32)
np.append(corner_list, point_1)
np.append(corner_list, point_2)
np.append(corner_list, point_3)
np.append(corner_list, point_4)
print("corners list")
print(corner_list)
myPointsNew = np.zeros((4, 1, 2), np.int32)
add = corner_list.sum(1)
# print(add)
# print(np.argmax(add))
myPointsNew[0] = corner_list[np.argmin(add)] #[0,0] #Setting up points in a coordinate system
myPointsNew[3] = corner_list[np.argmax(add)] #[w,h]
diff = np.diff(corner_list, axis=1)
myPointsNew[1] = corner_list[np.argmin(diff)] #[w,0]
myPointsNew[2] = corner_list[np.argmax(diff)] #[h,0]
print("mypointsnew")
print(myPointsNew.shape)
return myPointsNew
img_path = 'OMRsheet.jpg'
img = cv2.imread(img_path)
img_width = 700
img_height = 700
img = cv2.resize(img, (img_width, img_height), interpolation=cv2.INTER_AREA)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (5,5), 0) # blurred image
img_canny = cv2.Canny(img_blur, 20, 110) # Edge detection on processed image using Canny edge detection , binary thresholding could have been an alternative (i.e If the pixel value is smaller than the threshold, it is set to 0, otherwise it is set to a maximum value. )
contours, heirarchy = cv2.findContours(img_canny, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) # Find contours.
#parameters are (input_image, retrieval_mode, approximation_method)
img_contours = img.copy()
cv2.drawContours(img_contours, contours, -1, (0,255,0), 1) #parameters are (image, contours, countour_idx, contour_color, contour_thickness) . contour_idx is -1 for all contours
cv2.imshow('Contours', img_contours)
rect_contours = extract_rect(contours)
cv2.drawContours(img, rect_contours[1], -1, (0,255,0), 1)
rect_2 = rect_points(rect_contours[1])
cv2.drawContours(img, rect_2, -1, (0,0,255), 12)
warp_img_width = int(img_width/1.2)
warp_img_height = int(img_height/1.2)
warp_from = np.float32(rect_2)
warp_to = np.float32([[0,0], [warp_img_width, 0], [0, warp_img_height], [warp_img_width, warp_img_height]])
transformation_matrix = cv2.getPerspectiveTransform(warp_from, warp_to)
img_warp = cv2.warpPerspective(img, transformation_matrix, (warp_img_height, warp_img_height))
cv2.imshow('Warped Perspective', img_warp)
cv2.imshow('Original', img)
cv2.waitKey(0)
Output for cv2.imshow('Original', img) :- OMRsheet_contours.jpg
Output for cv2.imshow('Warped Perspective', img_warp) :-Bird's Eye perspective.jpg
EXPECTED Output for cv2.imshow('Warped Perspective', img_warp) :- Expected Bird's eye.jpg
Instead of getting warped perspective of the section containing only bubbles I am getting warped perspective for the whole paper which means either the points returned by rect_points function or the contour passed to the function i.e rect_contours[1] must have a mistake. The latter seemed to be fine as suggested after drawing contour lines for the contour passed to rect_points function. I suspect x, y, w, h = cv2.boundingRect(rect_contour) is returning incorrect points.
Any idea on how I could solve this problem and get the Expected Bird's eye.jpg ?
How can I go about trying to order the items of a picture from top left to bottom right, such as in the image below? Currently receiving this error with the following code .
Error:
a = sorted(keypoints, key=lambda p: (p[0]) + (p1))[0] # find upper left point
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
This question is modelled from this: Ordering coordinates from top left to bottom right
def preprocess(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (5, 5), 1)
img_canny = cv2.Canny(img_blur, 50, 50)
kernel = np.ones((3, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=2)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
return img_erode
image_final = preprocess(picture_example.png)
keypoints, hierarchy = cv2.findContours(image_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
points = []
while len(keypoints) > 0:
a = sorted(keypoints, key=lambda p: (p[0]) + (p[1]))[0] # find upper left point
b = sorted(keypoints, key=lambda p: (p[0]) - (p[1]))[-1] # find upper right point
cv2.line(image_final, (int(a.pt[0]), int(a.pt[1])), (int(b.pt[0]), int(b.pt[1])), (255, 0, 0), 1)
# convert opencv keypoint to numpy 3d point
a = np.array([a.pt[0], a.pt[1], 0])
b = np.array([b.pt[0], b.pt[1], 0])
row_points = []
remaining_points = []
for k in keypoints:
p = np.array([k.pt[0], k.pt[1], 0])
d = k.size # diameter of the keypoint (might be a theshold)
dist = np.linalg.norm(np.cross(np.subtract(p, a), np.subtract(b, a))) / np.linalg.norm(b) # distance between keypoint and line a->b
if d/2 > dist:
row_points.append(k)
else:
remaining_points.append(k)
points.extend(sorted(row_points, key=lambda h: h.pt[0]))
keypoints= remaining_points
New Picture:
Reference Ordering Picture:
Will use center of mass to determine center point ordering.
The resulting numbering depends on how many rows you want there to be. With the program I will show you how to make, you can specify the number of rows before you run the program.
For example, here is the original image:
Here is the numbered image when you specify 4 rows:
Here is the numbered image when you specify 6 rows:
For the other image you provided (with its frame cropped so the frame won't be detected as a shape), you can see there will be 4 rows, so putting 4 into the program will give you:
Let's have a look at the workflow considering 4 rows. The concept I used is to divide the image into 4 segments along the y axis, forming 4 rows. For each segment of the image, find every shape that has its center in that segment. Finally, order the shapes in each segment by their x coordinate.
Import the necessary libraries:
import cv2
import numpy as np
Define a function that will take in an image input and return the image processed to something that will allow python to later retrieve their contours:
def process_img(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_canny = cv2.Canny(img_gray, 100, 100)
kernel = np.ones((2, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
return img_erode
Define a function that will return the center of a contour:
def get_centeroid(cnt):
length = len(cnt)
sum_x = np.sum(cnt[..., 0])
sum_y = np.sum(cnt[..., 1])
return int(sum_x / length), int(sum_y / length)
Define a function that will take in a processed image and return the center points of the shapes found in the image:
def get_centers(img):
contours, hierarchies = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for cnt in contours:
if cv2.contourArea(cnt) > 100:
yield get_centeroid(cnt)
Define a function that will take in an image array, img, an array of coordinates, centers, the number of segments for the image, row_amt, and the height of each segment, row_h, as input. It will return row_amt arrays (sorted by their x coordinates), each containing every point in centers that lies in its corresponding row of the image:
def get_rows(img, centers, row_amt, row_h):
centers = np.array(centers)
d = row_h / row_amt
for i in range(row_amt):
f = centers[:, 1] - d * i
a = centers[(f < d) & (f > 0)]
yield a[a.argsort(0)[:, 0]]
Read in the image, get its processed form using the processed function defined, and get the center of each shape in the image using the centers function defined:
img = cv2.imread("shapes.png")
img_processed = process_img(img)
centers = list(get_centers(img_processed))
Get the height of the image to use for the get_rows function defined, and define a count variable, count, to keep track of the numbering:
h, w, c = img.shape
count = 0
Loop through the centers of the shape divided into 4 rows, drawing the line that connects the rows for visualization:
for row in get_rows(img, centers, 4, h):
cv2.polylines(img, [row], False, (255, 0, 255), 2)
for x, y in row:
Add to the count variable, and draw the count onto the specific location on the image from the row array:
count += 1
cv2.circle(img, (x, y), 10, (0, 0, 255), -1)
cv2.putText(img, str(count), (x - 10, y + 5), 1, cv2.FONT_HERSHEY_PLAIN, (0, 255, 255), 2)
Finally, show the image:
cv2.imshow("Ordered", img)
cv2.waitKey(0)
Altogether:
import cv2
import numpy as np
def process_img(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_canny = cv2.Canny(img_gray, 100, 100)
kernel = np.ones((2, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
return img_erode
def get_centeroid(cnt):
length = len(cnt)
sum_x = np.sum(cnt[..., 0])
sum_y = np.sum(cnt[..., 1])
return int(sum_x / length), int(sum_y / length)
def get_centers(img):
contours, hierarchies = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for cnt in contours:
if cv2.contourArea(cnt) > 100:
yield get_centeroid(cnt)
def get_rows(img, centers, row_amt, row_h):
centers = np.array(centers)
d = row_h / row_amt
for i in range(row_amt):
f = centers[:, 1] - d * i
a = centers[(f < d) & (f > 0)]
yield a[a.argsort(0)[:, 0]]
img = cv2.imread("shapes.png")
img_processed = process_img(img)
centers = list(get_centers(img_processed))
h, w, c = img.shape
count = 0
for row in get_rows(img, centers, 4, h):
cv2.polylines(img, [row], False, (255, 0, 255), 2)
for x, y in row:
count += 1
cv2.circle(img, (x, y), 10, (0, 0, 255), -1)
cv2.putText(img, str(count), (x - 10, y + 5), 1, cv2.FONT_HERSHEY_PLAIN, (0, 255, 255), 2)
cv2.imshow("Ordered", img)
cv2.waitKey(0)
This is not completly the same task as in your linked question you took the code from:
You have contours, while the other question has points.
You have to come up with a method to sort contours (they might overlap in one dimension and so on...). There are multiple ways to do that, depending on your use case. The easiest might be to use the center of mass of your contour. This can be done like here: Center of mass in contour (Python, OpenCV). Then you can make an array of objects out of it, that contain points and use the code that you found.
The code that you found assumes that the points are basically more or less on a grid. So all the points 1-5 on your reference image are roughly on a line. In the new picture you posted, this is not really the case. It might be better to go for a clustering approach here: Cluster the center points y coordinates with some aproach (maybe one from here). Then for each cluster: sort the elements by there centers x coordinate.
As I already said there are multiple ways in doing that and it depends hardly on your use case.
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)
Input Image
Processed Image
import numpy as np
import cv2
img = cv2.imread('Image(i).png', 0)
ret, img =cv2.threshold(img, 128, 255, cv2.THRESH_BINARY)
img_bw = img<=120
img_bw =img_bw.astype('uint8')
#Fit the ellipses
contours0, hierarchy = cv2.findContours( img.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
outer_ellipse = [cv2.approxPolyDP(contours0[0], 0.1, True)]
inner_ellipse = [cv2.approxPolyDP(contours0[0], 0.1, True)]
ref = np.zeros_like(img_bw)
out=img.copy()
h, w = img.shape[:2]
vis = np.zeros((h, w, 3), np.uint8)
cv2.drawContours( vis, outer_ellipse, -1, (255,0,0), 1)
cv2.drawContours( vis, inner_ellipse, -1, (0,0,255), 1)
##Extract contour of ellipses
cnt_outer = np.vstack(outer_ellipse).squeeze()
cnt_inner = np.vstack(inner_ellipse).squeeze()
#Determine centroid
M = cv2.moments(cnt_inner)
cx = int(M['m10']/M['m00'])
cy = int(M['m01']/M['m00'])
print (cx, cy)
#Draw full segment lines
#cv2.line(vis,(cx,0),(cx,w),(150,0,0),1)
width = img.shape[1]
height = img.shape[0]
N = 20
for i in range(N):
tmp = np.zeros_like(img_bw)
theta = i*(360/N)
theta *= np.pi/180.0
cv2.line(tmp, (cx, cy),
(int(cx-np.cos(theta)*w),
int(cy+np.sin(theta)*h)), (150,0,0), 1)
(row,col) = np.nonzero(np.logical_and(tmp, ref))
#cv2.line(out, (cx, cy), (col,row),(255,0,0), 1)
# Show the image
cv2.imshow('Output', out)
cv2.waitKey(0)
cv2.destroyAllWindows()
As seen in processed image the lines passing through centroid are not constricted till outer contour and are passing trough it.
I want the lines to be stopped at the outer contour so as that I can measure distance from centroid to the outer contour.
First image is the input image and second image is of line segments passing through centroid.
Here's a possible approach:
draw your outer contour filled with black on a white background
You now have a black ellipse. Then, without actually drawing anything:
use skimage.draw.line to get the list of points along all your radii
use Numpy argmax() to get first white pixel along radii
Here is the code:
#!/usr/bin/env python3
import cv2
import math
from skimage.draw import line
import numpy as np
# Load image as greyscale
img = cv2.imread('ellipses.png', cv2.IMREAD_GRAYSCALE)
_, img = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY)
h, w = img.shape
#Fit the ellipses
contours, hierarchy = cv2.findContours( img, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
outer_ellipse = [cv2.approxPolyDP(contours[0], 0.1, True)]
# Draw outer contour filled with black on white background
vis = np.zeros_like(img) + 255
cnt = cv2.drawContours(vis, outer_ellipse, -1, 0, -1)
# Centroid by existing method
cx, cy = 365, 335
maxThickness = 0
# Take 10 points along top
for x in range(0,w,int(w/10)):
# ... and bottom
for y in 0, h-1:
# Get y and x of all pixels between centroid and top and bottom edge
yy, xx = line(cy, cx, 0, x)
firstWhiteIndex = np.argmax(vis[yy,xx])
fx, fy = xx[firstWhiteIndex], yy[firstWhiteIndex]
# Get length of this radial line
length = np.sqrt((cx-fx)**2 + (cy-fy)**2)
# Remember if longer than all others so far seen
if length > maxThickness:
maxThickness = length
fxMax, fyMax = fx, fy
# Take 10 points down left side
for y in range(0,h,int(h/10)):
# ... and right
for x in 0, w-1:
# Get y and x of all pixels between centroid and left and right edge
yy, xx = line(cy, cx, 0, x)
firstWhiteIndex = np.argmax(vis[yy,xx])
fx, fy = xx[firstWhiteIndex], yy[firstWhiteIndex]
# Get length of this radial line
length = np.sqrt((cx-fx)**2 + (cy-fy)**2)
# Remember if longer than all others so far seen
if length > maxThickness:
maxThickness = length
fxMax, fyMax = fx, fy
print(f'Max thickness: {maxThickness}')
# Draw thickest radius in mid-grey
cv2.line(img, (cx,cy), (fxMax, fyMax), 128, 5)
cv2.imwrite('result.png', img)
I have an approach that is not the best but this is what I can think of now.
While drawing lines in the above image, modify the code and do the following:
Before the for loop, draw a binary image of the same size containing only the outer contour circle. Save this image for later use.
Now in the for loop, draw each line in a separate binary blank image. Thus, now you will have two images, first the image having only the outer circle, and second image will only contain the line.
Now perform a bitwise_and operation on these 2 images.
Now you will get a white pixel only that is the point of intersection of the line and the outer circle.
Now find the coordinates of the white pixel in the image found and hence you will have the coordinate of point of intersection.
Obviously this is not the most efficient way but it is real time. Also, keep this in mind that the outer circle width should be atleast 2 in the image and the lines should be of width 1. You may get more than one point of intersection in some cases, take any 1 of them. The difference in them will be only of 1-2 pixels that can be neglected.
if the squares has connected region in image, how can I detect them.
I have tested the method mentioned in
OpenCV C++/Obj-C: Advanced square detection
It did not work well.
Any good ideas ?
import cv2
import numpy as np
def angle_cos(p0, p1, p2):
d1, d2 = (p0-p1).astype('float'), (p2-p1).astype('float')
return abs( np.dot(d1, d2) / np.sqrt( np.dot(d1, d1)*np.dot(d2, d2) ) )
def find_squares(img):
squares = []
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# cv2.imshow("gray", gray)
gaussian = cv2.GaussianBlur(gray, (5, 5), 0)
temp,bin = cv2.threshold(gaussian, 80, 255, cv2.THRESH_BINARY)
# cv2.imshow("bin", bin)
contours, hierarchy = cv2.findContours(bin, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours( gray, contours, -1, (0, 255, 0), 3 )
#cv2.imshow('contours', gray)
for cnt in contours:
cnt_len = cv2.arcLength(cnt, True)
cnt = cv2.approxPolyDP(cnt, 0.02*cnt_len, True)
if len(cnt) == 4 and cv2.contourArea(cnt) > 1000 and cv2.isContourConvex(cnt):
cnt = cnt.reshape(-1, 2)
max_cos = np.max([angle_cos( cnt[i], cnt[(i+1) % 4], cnt[(i+2) % 4] ) for i in xrange(4)])
if max_cos < 0.1:
squares.append(cnt)
return squares
if __name__ == '__main__':
img = cv2.imread('123.bmp')
#cv2.imshow("origin", img)
squares = find_squares(img)
print "Find %d squres" % len(squares)
cv2.drawContours( img, squares, -1, (0, 255, 0), 3 )
cv2.imshow('squares', img)
cv2.waitKey()
I use some method in the opencv example, but the result is not good.
Applying a Watershed Transform based on the Distance Transform will separate the objects:
Handling objects at the border is always problematic, and often discarded, so that pink rectangle at top left not separated is not a problem at all.
Given a binary image, we can apply the Distance Transform (DT) and from it obtain markers for the Watershed. Ideally there would be a ready function for finding regional minima/maxima, but since it isn't there, we can make a decent guess on how we can threshold DT. Based on the markers we can segment using Watershed, and the problem is solved. Now you can worry about distinguishing components that are rectangles from those that are not.
import sys
import cv2
import numpy
import random
from scipy.ndimage import label
def segment_on_dt(img):
dt = cv2.distanceTransform(img, 2, 3) # L2 norm, 3x3 mask
dt = ((dt - dt.min()) / (dt.max() - dt.min()) * 255).astype(numpy.uint8)
dt = cv2.threshold(dt, 100, 255, cv2.THRESH_BINARY)[1]
lbl, ncc = label(dt)
lbl[img == 0] = lbl.max() + 1
lbl = lbl.astype(numpy.int32)
cv2.watershed(cv2.cvtColor(img, cv2.COLOR_GRAY2BGR), lbl)
lbl[lbl == -1] = 0
return lbl
img = cv2.cvtColor(cv2.imread(sys.argv[1]), cv2.COLOR_BGR2GRAY)
img = cv2.threshold(img, 0, 255, cv2.THRESH_OTSU)[1]
img = 255 - img # White: objects; Black: background
ws_result = segment_on_dt(img)
# Colorize
height, width = ws_result.shape
ws_color = numpy.zeros((height, width, 3), dtype=numpy.uint8)
lbl, ncc = label(ws_result)
for l in xrange(1, ncc + 1):
a, b = numpy.nonzero(lbl == l)
if img[a[0], b[0]] == 0: # Do not color background.
continue
rgb = [random.randint(0, 255) for _ in xrange(3)]
ws_color[lbl == l] = tuple(rgb)
cv2.imwrite(sys.argv[2], ws_color)
From the above image you can consider fitting ellipses in each component to determine rectangles. Then you can use some measurement to define whether the component is a rectangle or not. This approach has a greater chance to work for rectangles that are fully visible, and will likely produce bad results for partially visible ones. The following image shows the result of such approach considering that a component is a rectangle if the rectangle from the fitted ellipse is within 10% of component's area.
# Fit ellipse to determine the rectangles.
wsbin = numpy.zeros((height, width), dtype=numpy.uint8)
wsbin[cv2.cvtColor(ws_color, cv2.COLOR_BGR2GRAY) != 0] = 255
ws_bincolor = cv2.cvtColor(255 - wsbin, cv2.COLOR_GRAY2BGR)
lbl, ncc = label(wsbin)
for l in xrange(1, ncc + 1):
yx = numpy.dstack(numpy.nonzero(lbl == l)).astype(numpy.int64)
xy = numpy.roll(numpy.swapaxes(yx, 0, 1), 1, 2)
if len(xy) < 100: # Too small.
continue
ellipse = cv2.fitEllipse(xy)
center, axes, angle = ellipse
rect_area = axes[0] * axes[1]
if 0.9 < rect_area / float(len(xy)) < 1.1:
rect = numpy.round(numpy.float64(
cv2.cv.BoxPoints(ellipse))).astype(numpy.int64)
color = [random.randint(60, 255) for _ in xrange(3)]
cv2.drawContours(ws_bincolor, [rect], 0, color, 2)
cv2.imwrite(sys.argv[3], ws_bincolor)
Solution 1:
Dilate your image to delete connected components.
Find contours of detected components. Eliminate contours which are not rectangles by introducing some measure (ex. ratio perimeter / area).
This solution will not detect rectangles connected to borders.
Solution 2:
Dilate to delete connected components.
Find contours.
Approximate contours to reduce their points (for rectangle contour should be 4 points).
Check if angle between contour lines is 90 degrees.
Eliminate contours which have no 90 degrees.
This should solve problem with rectangles connected to borders.
You have three problems:
The rectangles are not very strict rectangles (the edges are often somewhat curved)
There are a lot of them.
They are often connected.
It seems that all your rects are essentially the same size(?), and do not greatly overlap, but the pre-processing has connected them.
For this situation the approach I would try is:
dilate your image a few times (as also suggested by #krzych) - this will remove the connections, but result in slightly smaller rects.
Use scipy to label and find_objects - You now know the position and slice for every remaining blob in the image.
Use minAreaRect to find the center, orientation, width and height of each rectangle.
You can use step 3. to test whether the blob is a valid rectangle or not, by its area, dimension ratio or proximity to the edge..
This is quite a nice approach, as we assume each blob is a rectangle, so minAreaRect will find the parameters for our minimum enclosing rectangle. Further we could test each blob using something like humoments if absolutely neccessary.
Here is what I was suggesting in action, boundary collision matches shown in red.
Code:
import numpy as np
import cv2
from cv2 import cv
import scipy
from scipy import ndimage
im_col = cv2.imread('jdjAf.jpg')
im = cv2.imread('jdjAf.jpg',cv2.CV_LOAD_IMAGE_GRAYSCALE)
im = np.where(im>100,0,255).astype(np.uint8)
im = cv2.erode(im, None,iterations=8)
im_label, num = ndimage.label(im)
for label in xrange(1, num+1):
points = np.array(np.where(im_label==label)[::-1]).T.reshape(-1,1,2).copy()
rect = cv2.minAreaRect(points)
lines = np.array(cv2.cv.BoxPoints(rect)).astype(np.int)
if any([np.any(lines[:,0]<=0), np.any(lines[:,0]>=im.shape[1]-1), np.any(lines[:,1]<=0), np.any(lines[:,1]>=im.shape[0]-1)]):
cv2.drawContours(im_col,[lines],0,(0,0,255),1)
else:
cv2.drawContours(im_col,[lines],0,(255,0,0),1)
cv2.imshow('im',im_col)
cv2.imwrite('rects.png',im_col)
cv2.waitKey()
I think the Watershed and distanceTransform approach demonstrated by #mmgp is clearly superior for segmenting the image, but this simple approach can be effective depending upon your needs.