Develop Reference

to detect patches in binary images using opencv python

I want to detect all the patches in the enter image description hereimage, I attached the code used to detect them:
import cv2
import numpy as np
import matplotlib.pyplot as plt
image=cv2.imread("bw2.jpg",0)
# convert to RGB
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
# create a binary thresholded image
_, binary = cv2.threshold(gray, 0, 500, cv2.THRESH_BINARY_INV)
# show it
plt.imshow(gray, cmap="gray")
plt.show()
# find the contours from the thresholded image
contours, hierarchy = cv2.findContours(gray, cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
print("contours:",contours)
# draw all contours
for c in contours:
if cv2.contourArea(c) < 3000:
continue
(x, y, w, h) = cv2.boundingRect(c)
#cv2.rectangle(image, (x,y), (x+w,y+h), (0, 255, 0), 2)
## BEGIN - draw rotated rectangle
rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(255,51,255),2)
# show the image with the drawn contours
plt.imshow(image)
#plt.imshow(im3)
cv2.imwrite("detectImg2.png",image)
plt.show()
I get output image as hereenter image description here
I want to detect all of them, can anyone tell me how to achieve this I new to image processing

Here is how I would extract and rotate each blob in your image using Python OpenCV.
Read the input
Convert to gray
Threshold
Apply morphology open and close to clean small spots
Get all the external contours
Loop over each contour and do the following:
Draw the contour on a copy of the input image
Get the rotated rectangle of the contour and extract its center, dimensions and rotation angle
Get the corners of the rotated rectangle
Draw the rotated rectangle on another copy of the input
Correct the rotation angle for image unrotation
Generate a mask image with the filled rotated rectangle
Apply the mask image to the morphology cleaned image to remove near-by other white regions
Get the affine warp matrix using the center and corrected rotation angle
Unrotated the the masked image using warpAffine
Get the contour of the one blob in the unrotated image
Get the contours bounding box
Crop the masked image (or alternately crop the input image)
Save the cropped image
Exit the loop
Save the contour and rotrect images
Input:
import cv2
import numpy as np
image = cv2.imread("bw2.jpg")
hh, ww = image.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# create a binary thresholded image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# apply morphology
kernel = np.ones((7,7), np.uint8)
clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = np.ones((13,13), np.uint8)
clean = cv2.morphologyEx(clean, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
contour_img = image.copy()
rotrect_img = image.copy()
i = 1
for c in contours:
# draw contour on input
cv2.drawContours(contour_img,[c],0,(0,0,255),2)
# get rotated rectangle from contour
# get its dimensions
# get angle relative to horizontal from rotated rectangle
rotrect = cv2.minAreaRect(c)
(center), (width,height), angle = rotrect
box = cv2.boxPoints(rotrect)
boxpts = np.int0(box)
# draw rotated rectangle on copy of image
cv2.drawContours(rotrect_img,[boxpts],0,(0,255,0),2)
# from https://www.pyimagesearch.com/2017/02/20/text-skew-correction-opencv-python/
# the `cv2.minAreaRect` function returns values in the
# range [-90, 0); as the rectangle rotates clockwise the
# returned angle tends to 0 -- in this special case we
# need to add 90 degrees to the angle
if angle < -45:
angle = -(90 + angle)
# otherwise, check width vs height
else:
if width > height:
angle = -(90 + angle)
else:
angle = -angle
# negate the angle for deskewing
neg_angle = -angle
# draw mask as filled rotated rectangle on black background the size of the input
mask = np.zeros_like(clean)
cv2.drawContours(mask,[boxpts],0,255,-1)
# apply mask to cleaned image
blob_img = cv2.bitwise_and(clean, mask)
# Get rotation matrix
#center = (width // 2, height // 2)
M = cv2.getRotationMatrix2D(center, neg_angle, scale=1.0)
#print('m: ',M)
# deskew (unrotate) the rotated rectangle
deskewed = cv2.warpAffine(blob_img, M, (ww, hh), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
# threshold it again
deskewed = cv2.threshold(deskewed, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# get bounding box of contour of deskewed rectangle
cntrs = cv2.findContours(deskewed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
cntr = cntrs[0]
x,y,w,h = cv2.boundingRect(cntr)
# crop to white region
crop = deskewed[y:y+h, x:x+w]
# alternately crop the input
#crop = image[y:y+h, x:x+w]
# save deskewed image
cv2.imwrite("bw2_deskewed_{0}.png".format(i),crop)
print("")
i = i + 1
# save contour and rot rect images
cv2.imwrite("bw2_contours.png",contour_img)
cv2.imwrite("bw2_rotrects.png",rotrect_img)
# display result, though it won't show transparency
cv2.imshow("thresh", thresh)
cv2.imshow("clean", clean)
cv2.imshow("contours", contour_img)
cv2.imshow("rectangles", rotrect_img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Contour image:
Rotated rectangles images:
First 3 unrotated images:
Affine warp rotation angles:
13.916877746582031
-42.87890625
18.8118896484375
-44.333797454833984
-38.65980911254883
-37.25965881347656
8.806793212890625
14.931419372558594
-37.405357360839844
-34.99202346801758
35.537681579589844
-35.350345611572266
-42.3245735168457
50.12316131591797
-42.969085693359375
52.750038146972656
45.0

your code is correct for detecting those patches, only a minor mistake is here
if cv2.contourArea(c) < 3000:
continue
reduce 3000 to 100 or below values, because your are giving a condition as contours below 3000 to be neglect

Extract already know shape from image

I´m trying to extract this piece
From this
Ive tried to detect shapes, no way, train an haarscascade...(Idont have negatives) no way, .... the position can vary (not all of them are inserted) and the angle is not the same.. I cannot crop one by one :-(
Any suggestion ??? Thanks in advance
PS Original image is here https://pasteboard.co/JaTSoJF.png (sorry > 2Mb)
After working on #ganeshtata we got
import cv2
import numpy as np
img = cv2.imread('cropsmall.png')
height, width = img.shape[:2]
green_channel = img[:,0:] # Blue channel extraction
res = cv2.fastNlMeansDenoising(green_channel, None, 3, 7, 21) # Non-local means denoising
cv2.imshow('denoised',res)
edges = cv2.Canny(res, 11, 11, 3) # Edge detection
kernel = np.ones((30, 30),np.uint8)
closing = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel) # Morphological closing
im2, contours, hierarchy = cv2.findContours(closing, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # Find all contours in the image
for cnt in contours: # Iterate through all contours
x, y, w, h = cv2.boundingRect(cnt) # Reject contours whose height is less than half the image height
if h < height / 2:
continue
y = 0 # Assuming that all shapes start from the top of the image
cv2.rectangle(img, (x, y), \
(x + w, y + h), (0, 255, 0), 2)
cv2.imshow('IMG',img)
cv2.imwrite("test.jpg",img)
cv2.waitKey(0)
That gives us
Not bad...

I used the following approach to extract the pattern specified in the question.
Read the image and extract the blue channel from the image.
import cv2
import numpy as np
img = cv2.imread('image.png')
height, width = img.shape[:2]
blue_channel = img[:,:,0]
Blue Channel -
Apply OpenCV's Non-local Means Denoising algorithm on the blue channel image. This ensures that most of the random noise in the image is smoothed.
res = cv2.fastNlMeansDenoising(blue_channel, None, 3, 7, 21)
Denoised image -
Apply Canny edge detection.
edges = cv2.Canny(res, 1, 10, 3)
Edge output -
Apply Morpological Closing to try and close small gaps/holes in the image.
kernel = np.ones((30, 30),np.uint8)
closing = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
Image after applying morphological closing -
Find all contours in the image using cv2.findContours. After finding all contours, we can determine the bounding box of each contour using cv2.boundingRect.
im2, contours, hierarchy = cv2.findContours(closing, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # Find all contours
for cnt in contours: # Iterate through all contours
x, y, w, h = cv2.boundingRect(cnt) $ Get contour bounding box
if h < height / 2: # Reject contours whose height is less than half the image height
continue
y = 0 # Assuming that all shapes start from the top of the image
cv2.rectangle(img, (x, y), \
(x + w, y + h), (0, 255, 0), 2)
Final result -
The complete code -
import cv2
import numpy as np
img = cv2.imread('image.png')
height, width = img.shape[:2]
blue_channel = img[:,:,0] # Blue channel extraction
res = cv2.fastNlMeansDenoising(blue_channel, None, 3, 7, 21) # Non-local means denoising
edges = cv2.Canny(res, 1, 10, 3) # Edge detection
kernel = np.ones((30, 30),np.uint8)
closing = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel) # Morphological closing
im2, contours, hierarchy = cv2.findContours(closing, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # Find all contours in the image
for cnt in contours: # Iterate through all contours
x, y, w, h = cv2.boundingRect(cnt) # Reject contours whose height is less than half the image height
if h < height / 2:
continue
y = 0 # Assuming that all shapes start from the top of the image
cv2.rectangle(img, (x, y), \
(x + w, y + h), (0, 255, 0), 2)
Note - This approach works for the sample image posted by you. It might/might not generalize for all images.

How I can detect recognize text in а shape

Need your help. Now I'm writing python script to recognize text in a shape. This shape can be captured from RTSP (IP Camera) at any angle.
For the example see attached file. My code is here, but coords to crop rotated shape is sets manually
import cv2
import numpy as np
def main():
fn = cv2.VideoCapture("rtsp://admin:Admin123-#172.16.10.254")
flag, img = fn.read()
cnt = np.array([
[[64, 49]],
[[122, 11]],
[[391, 326]],
[[308, 373]]
])
print("shape of cnt: {}".format(cnt.shape))
rect = cv2.minAreaRect(cnt)
print("rect: {}".format(rect))
box = cv2.boxPoints(rect)
box = np.int0(box)
print("bounding box: {}".format(box))
cv2.drawContours(img, [box], 0, (0, 255, 0), 2)
img_crop, img_rot = crop_rect(img, rect)
print("size of original img: {}".format(img.shape))
print("size of rotated img: {}".format(img_rot.shape))
print("size of cropped img: {}".format(img_crop.shape))
new_size = (int(img_rot.shape[1]/2), int(img_rot.shape[0]/2))
img_rot_resized = cv2.resize(img_rot, new_size)
new_size = (int(img.shape[1]/2)), int(img.shape[0]/2)
img_resized = cv2.resize(img, new_size)
cv2.imshow("original contour", img_resized)
cv2.imshow("rotated image", img_rot_resized)
cv2.imshow("cropped_box", img_crop)
# cv2.imwrite("crop_img1.jpg", img_crop)
cv2.waitKey(0)
def crop_rect(img, rect):
# get the parameter of the small rectangle
center = rect[0]
size = rect[1]
angle = rect[2]
center, size = tuple(map(int, center)), tuple(map(int, size))
# get row and col num in img
height, width = img.shape[0], img.shape[1]
print("width: {}, height: {}".format(width, height))
M = cv2.getRotationMatrix2D(center, angle, 1)
img_rot = cv2.warpAffine(img, M, (width, height))
img_crop = cv2.getRectSubPix(img_rot, size, center)
return img_crop, img_rot
if __name__ == "__main__":
main()
example pic

You may start with the example in the following post.
The code sample detects the license plate, and it also detects your "shape" with text.
After detecting the "shape" with the text, you may use the following stages:
Apply threshold the cropped area.
Find contours, and find the contour with maximum area.
Build a mask, and mask area outside the contour (like in the license plate example).
Use minAreaRect (as fmw42 commented), and get the angle of the rectangle.
Rotate the cropped area (by angle+90 degrees).
Apply OCR using pytesseract.image_to_string.
Here is the complete code:
import cv2
import numpy as np
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # I am using Windows
# Read the input image
img = cv2.imread('Admin123.jpg')
# Reused code:
# https://stackoverflow.com/questions/60977964/pytesseract-not-recognizing-text-as-expected/60979089#60979089
################################################################################
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #convert to grey scale
gray = cv2.bilateralFilter(gray, 11, 17, 17)
edged = cv2.Canny(gray, 30, 200) #Perform Edge detection
cnts = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
# loop over our contours
for c in cnts:
# approximate the contour
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
# if our approximated contour has four points, then
# we can assume that we have found our screen
if len(approx) == 4:
screenCnt = approx
break
# Masking the part other than the "shape"
mask = np.zeros(gray.shape,np.uint8)
new_image = cv2.drawContours(mask,[screenCnt],0,255,-1,)
new_image = cv2.bitwise_and(img,img,mask=mask)
# Now crop
(x, y) = np.where(mask == 255)
(topx, topy) = (np.min(x), np.min(y))
(bottomx, bottomy) = (np.max(x), np.max(y))
cropped = gray[topx:bottomx+1, topy:bottomy+1]
################################################################################
# Apply threshold the cropped area
_, thresh = cv2.threshold(cropped, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnts = imutils.grab_contours(cnts)
# Get contour with maximum area
c = max(cnts, key=cv2.contourArea)
# Build a mask (same as the code above)
mask = np.zeros(cropped.shape, np.uint8)
new_cropped = cv2.drawContours(mask, [c], 0, 255, -1)
new_cropped = cv2.bitwise_and(cropped, cropped, mask=mask)
# Draw green rectangle for testing
test = cv2.cvtColor(new_cropped, cv2.COLOR_GRAY2BGR)
cv2.drawContours(test, [c], -1, (0, 255, 0), thickness=2)
# Use minAreaRect as fmw42 commented
rect = cv2.minAreaRect(c)
angle = rect[2] # Get angle of the rectangle
# Rotate the cropped rectangle.
rotated_cropped = imutils.rotate(new_cropped, angle + 90)
# Read the text in the "shape"
text = pytesseract.image_to_string(rotated_cropped, config='--psm 3')
print("Extracted text is:\n\n", text)
# Show images for testing:
cv2.imshow('cropped', cropped)
cv2.imshow('thresh', thresh)
cv2.imshow('test', test)
cv2.imshow('rotated_cropped', rotated_cropped)
cv2.waitKey(0)
cv2.destroyAllWindows()
OCR output result:
AB12345
DEPARTMENT OF
INFORMATION
COMMUNICATION
TECHNOLOGY
cropped:
thresh:
test:
rotated_cropped:

Difficulty in detecting the outer circle with cv2.HoughCircles

I am trying to detect the outer boundary of the circular object in the images below:
I tried OpenCV's Hough Circle, but the code is not working for every image. I also tried to adjust parameters such as minRadius and maxRadius in Hough Circle but its not working on every image.
The aim is to detect the object from the image and crop it.
Expected output:
Source code:
import imutils
import cv2
import numpy as np
from matplotlib import pyplot as plt
image = cv2.imread("path to the image i have provided")
r = 600.0 / image.shape[1]
dim = (600, int(image.shape[0] * r))
resized = cv2.resize(image, dim, interpolation = cv2.INTER_AREA)
cv2.imwrite("path to were we want to save downscaled image", resized)
image = cv2.imread('path of downscaled image')
image1 = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image2 = cv2.GaussianBlur(image1, (5, 5), 0)
edged = cv2.Canny(image2, 30, 150)
img = cv2.medianBlur(image2,5)
cimg = cv2.cvtColor(img,cv2.COLOR_GRAY2BGR)
circles = cv2.HoughCircles(edged,cv2.HOUGH_GRADIENT,1,20,
param1=50,param2=30,minRadius=200,maxRadius=280)
circles = np.uint16(np.around(circles))
max_circle = max(circles[0,:], key=lambda x:x[2])
# print(max_circle)
# # Create mask
height,width = image1.shape
mask = np.zeros((height,width), np.uint8)
for i in [max_circle]:
cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)
masked_data = cv2.bitwise_and(image, image, mask=mask)
_,thresh = cv2.threshold(mask,1,255,cv2.THRESH_BINARY)
# Find Contour
contours = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[0]
x,y,w,h = cv2.boundingRect(contours[0])
# Crop masked_data
crop = masked_data[y:y+h,x:x+w]
#Code to close Window
cv2.imshow('OG',image)
cv2.imshow('Cropped ROI',crop)
cv2.imwrite("path to save roi image", crop)
cv2.waitKey(0)
cv2.destroyAllWindows()

Second Answer: an approach based on color segmentation.
While I was editing the question to improve it's readability and was inserting and resizing all the images from the link you shared to make it easier for everyone to visualize what you are trying to do, it occurred to me that this problem might be a better candidate for an approach based on segmentation by color:
This simpler (but clever) approach assumes that the reel appears pretty much in the same location and has more or less the same dimensions every time:
To discover the approximate color of the reel in the image, define a list of Regions of Interest (ROIs) to sample pixels from and determine the min and max color of that area in the HSV color space. The location and size of the ROI are values derived from the size of the image. In the images below, you can see the ROIs as draw as blue-ish rectangles:
Once the min and max HSV colors have been found, a threshold operation with cv2.inRange() can be executed to segment the reel:
Then, iterate though all the contours in the binary image and assume that the largest one represents the reel. Use this contour and draw it in a separate mask to be able to extract the pixels from original image:
At this stage, it is also possible to compute a bounding box for the contour and extract it's precise location to be able to perform a crop operation later and completely isolate the reel in the image:
This approach works for EVERY image shared on the question.
Source code:
import cv2
import numpy as np
import sys
# initialize global H, S, V values
min_global_h = 179
min_global_s = 255
min_global_v = 255
max_global_h = 0
max_global_s = 0
max_global_v = 0
# load input image from the cmd-line
filename = sys.argv[1]
img = cv2.imread(sys.argv[1])
if (img is None):
print('!!! Failed imread')
sys.exit(-1)
# create an auxiliary image for debugging purposes
dbg_img = img.copy()
# initiailize a list of Regions of Interest that need to be scanned to identify good HSV values to threhsold by color
w = img.shape[1]
h = img.shape[0]
roi_w = int(w * 0.10)
roi_h = int(h * 0.10)
roi_list = []
roi_list.append( (int(w*0.25), int(h*0.15), roi_w, roi_h) )
roi_list.append( (int(w*0.25), int(h*0.60), roi_w, roi_h) )
# convert image to HSV color space
hsv_img = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# iterate through the ROIs to determine the min/max HSV color of the reel
for rect in roi_list:
x, y, w, h = rect
x2 = x + w
y2 = y + h
print('ROI rect=', rect)
cropped_hsv_img = hsv_img[y:y+h, x:x+w]
h, s, v = cv2.split(cropped_hsv_img)
min_h = np.min(h)
min_s = np.min(s)
min_v = np.min(v)
if (min_h < min_global_h):
min_global_h = min_h
if (min_s < min_global_s):
min_global_s = min_s
if (min_v < min_global_v):
min_global_v = min_v
max_h = np.max(h)
max_s = np.max(s)
max_v = np.max(v)
if (max_h > max_global_h):
max_global_h = max_h
if (max_s > max_global_s):
max_global_s = max_s
if (max_v > max_global_v):
max_global_v = max_v
# debug: draw ROI in original image
cv2.rectangle(dbg_img, (x, y), (x2, y2), (255,165,0), 4) # red
cv2.imshow('ROIs', cv2.resize(dbg_img, dsize=(0, 0), fx=0.5, fy=0.5))
#cv2.waitKey(0)
cv2.imwrite(filename[:-4] + '_rois.png', dbg_img)
# define min/max color for threshold
low_hsv = np.array([min_h, min_s, min_v])
max_hsv = np.array([max_h, max_s, max_v])
#print('low_hsv=', low_hsv)
#print('max_hsv=', max_hsv)
# threshold image by color
img_bin = cv2.inRange(hsv_img, low_hsv, max_hsv)
cv2.imshow('binary', cv2.resize(img_bin, dsize=(0, 0), fx=0.5, fy=0.5))
cv2.imwrite(filename[:-4] + '_binary.png', img_bin)
#cv2.imshow('img_bin', cv2.resize(img_bin, dsize=(0, 0), fx=0.5, fy=0.5))
#cv2.waitKey(0)
# create a mask to store the contour of the reel (hopefully)
mask = np.zeros((img_bin.shape[0], img_bin.shape[1]), np.uint8)
crop_x, crop_y, crop_w, crop_h = (0, 0, 0, 0)
# iterate throw all the contours in the binary image:
# assume that the first contour with an area larger than 100k belongs to the reel
contours, hierarchy = cv2.findContours(img_bin, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for contourIdx, cnt in enumerate(contours):
area = cv2.contourArea(contours[contourIdx])
print('contourIdx=', contourIdx, 'area=', area)
# draw potential reel blob on the mask (in white)
if (area > 100000):
crop_x, crop_y, crop_w, crop_h = cv2.boundingRect(cnt)
centers, radius = cv2.minEnclosingCircle(cnt)
cv2.circle(mask, (int(centers[0]), int(centers[1])), int(radius), (255), -1) # fill with white
break
cv2.imshow('mask', cv2.resize(mask, dsize=(0, 0), fx=0.5, fy=0.5))
cv2.imwrite(filename[:-4] + '_mask.png', mask)
# copy just the reel area into its own image
reel_img = cv2.bitwise_and(img, img, mask=mask)
cv2.imshow('reel_img', cv2.resize(reel_img, dsize=(0, 0), fx=0.5, fy=0.5))
cv2.imwrite(filename[:-4] + '_reel.png', reel_img)
# crop the reel to a smaller image
if (crop_w != 0 and crop_h != 0):
cropped_reel_img = reel_img[crop_y:crop_y+crop_h, crop_x:crop_x+crop_w]
cv2.imshow('cropped_reel_img', cv2.resize(cropped_reel_img, dsize=(0, 0), fx=0.5, fy=0.5))
output_filename = filename[:-4] + '_crop.png'
cv2.imwrite(output_filename, cropped_reel_img)
cv2.waitKey(0)

First answer: an approach based on pre-processing the image and executing an adaptiveThreshold operation.
There might be other ways of solving this problem that are not based on Hough Circles. Here is the result of an approach that is not:
Preprocess the image! Decreasing the size of the image and executing a blur helps with segmentation:
The segmentation method uses a cv2.adaptiveThreshold() to create a binary image that preserves the most important objects: the center of the reel and the external edge of the reel. This is an important step since we are only interested in what exists between these two objects. However, life is not perfect and neither is this segmentation. The shadow of reel on the table became part of the binary objects detected. Also, the outer edge is not fully connected as you can see on the resulting image on the right (look at the top left of the circumference):
To join broken segments, a morphological operation can be executed:
Finally, the entire reel area can be exposed by iterating through the contours of the image above and discarding those whose area is larger than what is expected for a reel. The resulting binary image (on the left) can then be used as a mask to identify the reel location on the original image:
Keep in mind that I'm not trying to find an universal solution for your problem. I'm merely showing that there might be other solutions that don't depend on Hough Circles.
Also, this code might need some adjustments to work on a larger number of cases.
Source code:
import cv2
import numpy as np
import sys
img = cv2.imread("test_images/reel.jpg")
if (img is None):
print('!!! Failed imread')
sys.exit(-1)
# create output image
output_img = img.copy()
# 1. Preprocess the image: downscale to speed up processing and execute a blur
SCALE_FACTOR = 0.5
smaller_img = cv2.resize(img, dsize=(0, 0), fx=SCALE_FACTOR, fy=SCALE_FACTOR)
blur_img = cv2.medianBlur(smaller_img, 9)
cv2.imwrite('reel1_blur_img.png', blur_img)
# 2. Segment the image to identify the 2 most important contours: the center of the reel and the outter edge
gray_img = cv2.cvtColor(blur_img, cv2.COLOR_BGR2GRAY)
img_bin = cv2.adaptiveThreshold(gray_img, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 19, 4)
cv2.imwrite('reel2_img_bin.png', img_bin)
green_mask = np.zeros((img_bin.shape[0], img_bin.shape[1]), np.uint8)
#green_mask = cv2.cvtColor(img_bin, cv2.COLOR_GRAY2RGB) # debug
contours, hierarchy = cv2.findContours(img_bin, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for contourIdx, cnt in enumerate(contours):
x, y, w, h = cv2.boundingRect(cnt)
area = cv2.contourArea(contours[contourIdx])
#print('contourIdx=', contourIdx, 'w=', w, 'h=', h, 'area=', area)
# filter out tiny segments
if (area < 5000):
#cv2.fillPoly(green_mask, pts=[cnt], color=(0, 0, 255)) # red
continue
# draw green contour (filled)
#cv2.fillPoly(green_mask, pts=[cnt], color=(0, 255, 0)) # green
cv2.fillPoly(green_mask, pts=[cnt], color=(255)) # white
# debug:
#cv2.imshow('green_mask', green_mask)
#cv2.waitKey(0)
cv2.imshow('green_mask', green_mask)
cv2.imwrite('reel2_green_mask.png', green_mask)
# 3. Fix mask: join segments nearby
kernel = np.ones((3,3), np.uint8)
img_dilation = cv2.dilate(green_mask, kernel, iterations=1)
green_mask = cv2.erode(img_dilation, kernel, iterations=1)
cv2.imshow('fixed green_mask', green_mask)
cv2.imwrite('reel3_img.png', green_mask)
# 4. Extract the reel area from the green mask
reel_mask = np.zeros((green_mask.shape[0], green_mask.shape[1]), np.uint8)
#reel_mask = cv2.cvtColor(green_mask, cv2.COLOR_GRAY2RGB) # debug
contours, hierarchy = cv2.findContours(green_mask, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for contourIdx, cnt in enumerate(contours):
x, y, w, h = cv2.boundingRect(cnt)
area = cv2.contourArea(contours[contourIdx])
print('contourIdx=', contourIdx, 'w=', w, 'h=', h, 'area=', area)
# filter out smaller segments
if (area > 110000):
#cv2.fillPoly(reel_mask, pts=[cnt], color=(0, 0, 255)) # red
continue
# draw green contour (filled)
#cv2.fillPoly(reel_mask, pts=[cnt], color=(0, 255, 0)) # green
cv2.fillPoly(reel_mask, pts=[cnt], color=(255)) # white
# debug:
#cv2.imshow('reel_mask', reel_mask)
#cv2.waitKey(0)
cv2.imshow('reel_mask', reel_mask)
cv2.imwrite('reel4_reel_mask.png', reel_mask)
# 5. Draw the reel area on the original image
contours, hierarchy = cv2.findContours(reel_mask, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for contourIdx, cnt in enumerate(contours):
centers, radius = cv2.minEnclosingCircle(cnt)
# rescale these values back to the original image size
centers_orig = (centers[0] // SCALE_FACTOR, centers[1] // SCALE_FACTOR)
radius_orig = radius // SCALE_FACTOR
print('centers=', centers_orig, 'radius=', radius_orig)
cv2.circle(output_img, (int(centers_orig[0]), int(centers_orig[1])), int(radius_orig), (128,0,255), 5) # magenta
cv2.imshow('output_img', output_img)
cv2.imwrite('reel5_output.png', output_img)
# display just the pixels from the original image
larger_reel_mask = cv2.resize(reel_mask, (int(img.shape[1]), int(img.shape[0])))
output_reel_img = cv2.bitwise_and(img, img, mask=larger_reel_mask)
cv2.imshow('output_reel_img', output_reel_img)
cv2.imwrite('reel5_output_reel.png', output_reel_img)
cv2.waitKey(0)
At this point, its possible to use larger_reel_maskand compute a minimal enclosing circle, draw it over this mask to make it a little bit more round and allow us to retrieve the area of the reel more accurately:
But the 4 lines of code that achieve this improvement I leave as an exercise for the reader.

How to center the content/object of a binary image in python?

I have a code that computes the orientation of a figure. Based on this orientation the figure is then rotated until it is straightened out. This all works fine. What I am struggling with, is getting the center of the rotated figure to the center of the whole image. So the center point of the figure should match the center point of the whole image.
Input image:
code:
import cv2
import numpy as np
import matplotlib.pyplot as plt
path = "inputImage.png"
image=cv2.imread(path)
gray=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh=cv2.threshold(gray,0,255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
contours,hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
cnt1 = contours[0]
cnt=cv2.convexHull(contours[0])
angle = cv2.minAreaRect(cnt)[-1]
print("Actual angle is:"+str(angle))
rect = cv2.minAreaRect(cnt)
p=np.array(rect[1])
if p[0] < p[1]:
print("Angle along the longer side:"+str(rect[-1] + 180))
act_angle=rect[-1]+180
else:
print("Angle along the longer side:"+str(rect[-1] + 90))
act_angle=rect[-1]+90
#act_angle gives the angle of the minAreaRect with the vertical
if act_angle < 90:
angle = (90 + angle)
print("angleless than -45")
# otherwise, just take the inverse of the angle to make
# it positive
else:
angle=act_angle-180
print("grter than 90")
# rotate the image to deskew it
(h, w) = image.shape[:2]
print(h,w)
center = (w // 2, h // 2)
print(center)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h),flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
plt.imshow(rotated)
cv2.imwrite("rotated.png", rotated)
With output:
As you can see the white figure is slightly placed to left, I want it to be perfectly centered.
Does anyone know how this can be done?
EDIT: I have tried #joe's suggestion and subtracted the centroid coordinates, from the center of the image by dividing the width and height of the picture by 2. From this I got an offset, this had to be added to the array that describes the image. But I don't know how I add the offset to the array. How would this work with the x and y coordinates?
The code:
img = cv2.imread("inputImage")
gray_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray_image,127,255,0)
height, width = gray_image.shape
print(img.shape)
wi=(width/2)
he=(height/2)
print(wi,he)
M = cv2.moments(thresh)
cX = int(M["m10"] / M["m00"])
cY = int(M["m01"] / M["m00"])
offsetX = (wi-cX)
offsetY = (he-cY)
print(offsetX,offsetY)
print(cX,cY)

Here is one way in Python/OpenCV.
Get the bounding box for the white region from the contours. Compute the offset for the recentered region. Use numpy slicing to copy that to the center of a black background the size of the input.
Input:
import cv2
import numpy as np
# read image as grayscale
img = cv2.imread('white_shape.png', cv2.COLOR_BGR2GRAY)
# get shape
hh, ww = img.shape
# get contours (presumably just one around the nonzero pixels)
contours = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
# recenter
startx = (ww - w)//2
starty = (hh - h)//2
result = np.zeros_like(img)
result[starty:starty+h,startx:startx+w] = img[y:y+h,x:x+w]
# view result
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
# save reentered image
cv2.imwrite('white_shape_centered.png',result)

One approach is to obtain the bounding box coordinates of the binary object then crop the ROI using Numpy slicing. From here we calculate the new shifted coordinates then paste the ROI onto a new blank mask.
Code
import cv2
import numpy as np
# Load image as grayscale and obtain bounding box coordinates
image = cv2.imread('1.png', 0)
height, width = image.shape
x,y,w,h = cv2.boundingRect(image)
# Create new blank image and shift ROI to new coordinates
mask = np.zeros(image.shape, dtype=np.uint8)
ROI = image[y:y+h, x:x+w]
x = width//2 - ROI.shape[0]//2
y = height//2 - ROI.shape[1]//2
mask[y:y+h, x:x+w] = ROI
cv2.imshow('ROI', ROI)
cv2.imshow('mask', mask)
cv2.waitKey()

#NawinNarain, from this point onwards where you found out the relative shifts w.r.t. centroid of the image, it is very straightforward - You want to make an Affine matrix with this translations and apply cv2.warpAffine() to your image. That's -it.
T = np.float32([[1, 0, shift_x], [0, 1, shift_y]])
We then use warpAffine() to transform the image using the matrix, T
centered_image = cv2.warpAffine(image, T, (orig_width, orig_height))
This will transform your image so that the centroid is at the center. Hope this helps. The complete center image function will look like this:
def center_image(image):
height, width = image.shape
print(img.shape)
wi=(width/2)
he=(height/2)
print(wi,he)
ret,thresh = cv2.threshold(image,95,255,0)
M = cv2.moments(thresh)
cX = int(M["m10"] / M["m00"])
cY = int(M["m01"] / M["m00"])
offsetX = (wi-cX)
offsetY = (he-cY)
T = np.float32([[1, 0, offsetX], [0, 1, offsetY]])
centered_image = cv2.warpAffine(image, T, (width, height))
return centered_image