Get the real bounding box of a rectangle shaped mask - python

i have this binary image (numpy array) that represents an approximation of a rectangle :
I'm trying to extract the real shape of the rectangle but can't seem to find a way.
The expected result is the following:
I'm using this code
contours,_ = cv2.findContours(numpymask.copy(), 1, 1) # not copying here will throw an error
rect = cv2.minAreaRect(contours[0]) # basically you can feed this rect into your classifier
(x,y),(w,h), a = rect # a - angle
box = cv2.boxPoints(rect)
box = np.int0(box) #turn into ints
rect2 = cv2.drawContours(img.copy(),[box],0,(0,0,255),10)
plt.imshow(rect2)
plt.show()
But the resut i'm getting is the following, which i not what i need :
For this i'm using Python with opencv.

This is something i played around with before. It should work with your image.
import imutils
import cv2
# load the image, convert it to grayscale, and blur it slightly
image = cv2.imread("test.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0)
# threshold the image,
thresh = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY)[1]
# find contours in thresholded image, then grab the largest
# one
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
# draw the contours of c
cv2.drawContours(image, [c], -1, (0, 0, 255), 2)
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)

Related

Fill the inside of unconnected contours

I have the following image: mask
I'm trying separate each white piece into its own image. My approach is to find the contours, iterate over them and fill each one with white color then save the new image.
So far, I've found the contours after using Canny Edge Detection: contours
But I can't seem to fill them all on the inside, since the edges are not fully connected:contours filled
Is there a way to fill in the contours without using dilation/erosion? I intend to preserve the image as it is, not altering it more than needed.
I've used the following code.
import cv2
import numpy as np
def get_blank_image(image):
return np.zeros((image.shape[0], image.shape[1], 3), np.uint8)
# Let's load a simple image with 3 black squares
image = cv2.imread('img.png')
cv2.waitKey(0)
blank_image = get_blank_image(image)
# cv2.imshow('blank', blank_image)
# Grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Find Canny edges
edged = cv2.Canny(gray, 30, 50)
cv2.waitKey(0)
# Finding Contours
# Use a copy of the image e.g. edged.copy()
# since findContours alters the image
contours, hierarchy = cv2.findContours(edged, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
good_contours = []
for con in contours:
area = cv2.contourArea(con)
if area > 10:
good_contours.append(con)
cv2.drawContours(blank_image, [con], 0, (255, 255, 255), thickness=cv2.FILLED)
# cv2.fillPoly(blank_image, pts=[con], color=(255, 255, 255))
# cv2.imshow('blank', blank_image)
# cv2.waitKey(0)
# good_contours.remove(con)
# cv2.imshow('Canny Edges After Contouring', edged)
cv2.waitKey(0)
cv2.imshow('blank', blank_image)
print("Number of Contours found = " + str(len(good_contours)))
# Draw all contours
# -1 signifies drawing all contours
cv2.drawContours(image, good_contours, -1, (0, 255, 0), 3)
cv2.imshow('Contours', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

Python - cv2 find Contours

I would like to find all the big elements in the document, but I do not know how to control the size (the document is downloaded from the Internet :))
I have a document
And I wrote a simple code
import cv2
import pytesseract
image = cv2.imread('2.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7, 7), 0)
thresh = cv2.threshold(
blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernal = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 50))
dilate = cv2.dilate(thresh, kernal, iterations=1)
cv2.imwrite('1_dilated.png', dilate)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=lambda x: cv2.boundingRect(x)[1])
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
if h > 100 and w > 100:
roi = image[y:y+h, x:x+w]
cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 2)
# ocr = pytesseract.image_to_string(roi)
# print(ocr)
cv2.imwrite('1_boxes4.png', image)
But only detects it
And I would like this
How to control the size of the detected area ?
Thank you very much for all your comments
You are close, but you need to increase the number of iterations of the dilate operation. Also, a rectangular structuring element might help better forming the blobs of text. Let's check out some possible improvements of your code:
# imports:
import cv2
import numpy as np
# Set image path
imagePath = "D://opencvImages//"
imageName = "F74Yq.png"
# Read image:
inputImage = cv2.imread(imagePath + imageName)
# Store a deeep copy for results:
inputCopy = inputImage.copy()
# Convert BGR to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Threshold via Otsu
_, binaryImage = cv2.threshold(grayInput, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
The first part produces the binary image of the input image, there's nothing fancy going on here - just a direct thresholding via Otsu's method. This is the binary image obtained:
Now, let's apply the dilate operation. Let's use a 9 x 9 rectangular kernel and set the number of iterations to 5. Gotta be careful you don't dilate too much, because blobs of text from different portions of the document could end up joined:
# Set kernel (structuring element) size:
kernelSize = (9, 9)
# Set operation iterations:
opIterations = 5
# Get the structuring element:
morphKernel = cv2.getStructuringElement(cv2.MORPH_RECT, kernelSize)
# Perform Dilate:
dilateImage = cv2.morphologyEx(binaryImage, cv2.MORPH_DILATE, morphKernel, None, None, opIterations, cv2.BORDER_REFLECT101)
This is the result:
Ok, now let's just detect external contours and get their bounding boxes so we can draw rectangles around the target areas. Note that I'm drawing the rectangles on a deep copy of the input:
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(dilateImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get the contours bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rectangle:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Set bounding rectangle:
color = (0, 0, 255)
cv2.rectangle( inputCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 5 )
cv2.imshow("Bounding Rectangles", inputCopy)
cv2.waitKey()
This is the final result:

detect an initial/a sketch drawing on a text page

I would like to get the coordinates of the box around the initial ("H") on the following page (and similar ones with other initials, so opencv template matching is not an option):
Following this tutorial, I tried to solve the problem with opencv contours:
import cv2
import matplotlib.pyplot as plt
page = "image.jpg"
# read the image
image = cv2.imread(page)
# 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, 0,150,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# find the contours from the thresholded image
contours, hierarchy = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# draw all contours
image = cv2.drawContours(image, contours, 3, (0, 255, 0), 2)
plt.savefig("result.png")
The result is of course not exactly what I wanted:
Does anyone know of an viable algorithm (and possibly an implementation thereof) that could provide an easy solution to my task?
You can find the target area by filtering your contours. Now, there's at least two filtering criteria that you can use. One is filter by area - that is, discard too small and too large contours until you get the contour you are looking for. The other one is by computing the extent of every contour. The extent is the ratio of the contour's area to its bounding rectangle area. You are looking for a square-like contour, so its extent should be close to 1.0.
Let's see the code:
# imports:
import cv2
import numpy as np
# Reading an image in default mode:
inputImage = cv2.imread(path + fileName)
# Deep copy for results:
inputImageCopy = inputImage.copy()
# Convert RGB to grayscale:
grayscaleImage = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Get binary image via Otsu:
_, binaryImage = cv2.threshold(grayscaleImage, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
The first portion of the code gets you a binary image that you can use as a mask to compute contours:
Now, let's filter contours. Let's use the area approach first. You need to define a range of minimum area and maximum area to filter everything that does not fall in this range. I've heuristically determined a range of areas from 30000 px to 150000 px:
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(binaryImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get blob area:
currentArea = cv2.contourArea(c)
print("Contour Area: "+str(currentArea))
# Set an area range:
minArea = 30000
maxArea = 150000
if minArea < currentArea < maxArea:
# Get the contour's bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rect:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Set bounding rect:
color = (0, 0, 255)
cv2.rectangle( inputImageCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 2 )
cv2.imshow("Rectangles", inputImageCopy)
cv2.waitKey(0)
Once you successfully filter the area, you can then compute the bounding rectangle of the contour with cv2.boundingRect. You can retrieve the bounding rectangle's x, y (top left) coordinates as well as its width and height. After that just draw the rectangle on a deep copy of the original input.
Now, let's see the second option, using the contour's extent. The for loop gets modified as follows:
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get blob area:
currentArea = cv2.contourArea(c)
# Get the contour's bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rect:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Calculate extent:
extent = float(currentArea)/(rectWidth *rectHeight)
print("Extent: " + str(extent))
# Set the extent filter, look for an extent close to 1.0:
delta = abs(1.0 - extent)
epsilon = 0.1
if delta < epsilon:
# Set bounding rect:
color = (0, 0, 255)
cv2.rectangle( inputImageCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 2 )
cv2.imshow("Rectangles", inputImageCopy)
cv2.waitKey(0)
Both approaches yield this result:
You almost have it. You just need to filter contours on area and aspect ratio. Here is my approach in Python/OpenCV.
Input:
import cv2
import numpy as np
# read image as grayscale
img = cv2.imread('syriados.jpg')
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold to binary
#thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# invert threshold
thresh = 255 - thresh
# apply morphology to remove small white regions and to close the rectangle boundary
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# find contours
result = img.copy()
cntrs = cv2.findContours(morph, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
# filter on area and aspect ratio
for c in cntrs:
area = cv2.contourArea(c)
x,y,w,h = cv2.boundingRect(c)
if area > 10000 and abs(w-h) < 100:
cv2.drawContours(result, [c], 0, (0,0,255), 2)
# write results
cv2.imwrite("syriados_thresh.jpg", thresh)
cv2.imwrite("syriados_morph.jpg", morph)
cv2.imwrite("syriados_box.jpg", result)
# show results
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
Threshold image:
Morphology image:
Resulting contour image:
To get a result like this:
You'll need to detect the contour in the image with the second to the greatest area, as the one possessing the greatest area would be the border of the image.
So with the list of contours, we can get the one with the second greatest area via the built-in sorted method, using the cv2.contourArea method as the custom key:
import cv2
import numpy as np
def process(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (7, 7), 2)
img_canny = cv2.Canny(img_blur, 50, 50)
kernel = np.ones((6, 6))
img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
img_erode = cv2.erode(img_dilate, kernel, iterations=2)
return img_erode
def get_contours(img):
contours, _ = cv2.findContours(process(img), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnt = sorted(contours, key=cv2.contourArea)[-2]
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.02 * peri, True)
cv2.drawContours(img, [approx], -1, (0, 255, 0), 2)
page = "image.jpg"
image = cv2.imread(page)
get_contours(image)
cv2.imshow("Image", image)
cv2.waitKey(0)
The above only puts the area of the contours into consideration; if you want more reliable results, you can make it so that it will only detect contours that are 4-sided.

How to find the center of black objects in an image with python opencv?

I have a problem finding the contours of black objects on white background.
here I added an example of an image.
Now I need to find center of black regions and I use following code.
im = cv2.imread(img)
plt.imshow(im)
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
thresh = cv2.threshold(im, 60, 255, cv2.THRESH_BINARY_INV)
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
However it gives an error like
TypeError: Expected Ptr for argument 'image' " for the image argument of cv2.findeContours().
How can I solve this? or if you have any other idea how to find center of black regions I would like to hear. Thanks.
You're on the right track. When you perform find contours on your image, OpenCV expects that the foreground objects to detect are in white with the background in black. To do this, you can Otsu's threshold with the cv2.THRESH_BINARY_INV parameter to get the objects in white. From here we can find contours and find the center of each region by calculating for the centroid with cv2.moments. Here's the results:
Binary image
Center of object drawn in blue with the bounding box in green. You can get the coordinates of each contour by checking the cX and cY variables.
You can crop each individual ROI using Numpy slicing then save with cv2.imwrite
Code
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, Otsu's threshold
image = cv2.imread('1.png')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Find contours
ROI_number = 0
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
# Obtain bounding rectangle to get measurements
x,y,w,h = cv2.boundingRect(c)
# Find centroid
M = cv2.moments(c)
cX = int(M["m10"] / M["m00"])
cY = int(M["m01"] / M["m00"])
# Crop and save ROI
ROI = original[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
ROI_number += 1
# Draw the contour and center of the shape on the image
cv2.rectangle(image,(x,y),(x+w,y+h),(36,255,12), 4)
cv2.circle(image, (cX, cY), 10, (320, 159, 22), -1)
cv2.imwrite('image.png', image)
cv2.imwrite('thresh.png', thresh)
cv2.waitKey()

Finding the corners of a rectangle

I'm trying to get the corners of this rectangle:
.
I tried using cv2.cornerHarris(rectangle, 2, 3, 0.04), but the left edges are not showed due to image brightness, I guess. So I tried applying a threshold before using cornerHarris, but the image produced showed a lot of vertices along the edges, not being possible to filter the corners.
I know that I need to filter it before using cornerHarris, but I don't know how. Could someone help me with this problem?
Ps. I've already tried to use blur, but it also doesn't work.
import cv2
import numpy as np
import matplotlib.pyplot as plt
rectangle = cv2.imread('rectangle.png', cv2.IMREAD_GRAYSCALE)
rectangle = np.where(rectangle > np.mean(rectangle), 255, 0).astype(np.uint8)
dst_rectangle = cv2.cornerHarris(rectangle, 2, 3, 0.04)
dst_rectangle = cv2.dilate(dst_rectangle, None)
mask = np.where(dst_rectangle > 0.01*np.max(dst_rectangle), 255, 0).astype(np.uint8)
points = np.nonzero(mask)
plt.imshow(dst_rectangle, cmap='gray')
plt.plot(points[1], points[0], 'or')
plt.show()
I would approach it differently by getting the corners of the rotated bounding box of the contour after adaptive thresholding. Here is my code in Python/OpenCV.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread("rectangle.png")
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = 255-gray
# do adaptive threshold on gray image
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 17, 1)
thresh = 255-thresh
# apply morphology
kernel = np.ones((3,3), np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# separate horizontal and vertical lines to filter out spots outside the rectangle
kernel = np.ones((7,3), np.uint8)
vert = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
kernel = np.ones((3,7), np.uint8)
horiz = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# combine
rect = cv2.add(horiz,vert)
# thin
kernel = np.ones((3,3), np.uint8)
rect = cv2.morphologyEx(rect, cv2.MORPH_ERODE, kernel)
# get largest contour
contours = cv2.findContours(rect, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for c in contours:
area_thresh = 0
area = cv2.contourArea(c)
if area > area_thresh:
area = area_thresh
big_contour = c
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(big_contour)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
print(box)
# draw rotated rectangle on copy of img
rot_bbox = img.copy()
cv2.drawContours(rot_bbox,[box],0,(0,0,255),2)
# write img with red rotated bounding box to disk
cv2.imwrite("rectangle_thresh.png", thresh)
cv2.imwrite("rectangle_outline.png", rect)
cv2.imwrite("rectangle_bounds.png", rot_bbox)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("VERT", vert)
cv2.imshow("HORIZ", horiz)
cv2.imshow("RECT", rect)
cv2.imshow("BBOX", rot_bbox)
cv2.waitKey(0)
Thresholded Image:
Rectangle Region Extracted:
Rotated Bounding Box on Image:
Rotated Bounding Box Corners:
[[446 335]
[163 328]
[168 117]
[451 124]]
ADDITION:
Here is a slightly shorter version of the code, which is achievable by adding some gaussian blurring before thresholding.
import cv2
import numpy as np
# read image
img = cv2.imread("rectangle.png")
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = 255-gray
# blur image
blur = cv2.GaussianBlur(gray, (3,3), 0)
# do adaptive threshold on gray image
thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 75, 2)
thresh = 255-thresh
# apply morphology
kernel = np.ones((5,5), np.uint8)
rect = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
rect = cv2.morphologyEx(rect, cv2.MORPH_CLOSE, kernel)
# thin
kernel = np.ones((5,5), np.uint8)
rect = cv2.morphologyEx(rect, cv2.MORPH_ERODE, kernel)
# get largest contour
contours = cv2.findContours(rect, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for c in contours:
area_thresh = 0
area = cv2.contourArea(c)
if area > area_thresh:
area = area_thresh
big_contour = c
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(big_contour)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
for p in box:
pt = (p[0],p[1])
print(pt)
# draw rotated rectangle on copy of img
rot_bbox = img.copy()
cv2.drawContours(rot_bbox,[box],0,(0,0,255),2)
# write img with red rotated bounding box to disk
cv2.imwrite("rectangle_thresh.png", thresh)
cv2.imwrite("rectangle_outline.png", rect)
cv2.imwrite("rectangle_bounds.png", rot_bbox)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("RECT", rect)
cv2.imshow("BBOX", rot_bbox)
cv2.waitKey(0)
Thresholded Image:
Rectangle Region Extracted:
Rotated Bounding Box on Image:
Rotated Bounding Box Corners:
(444, 335)
(167, 330)
(170, 120)
(448, 125)
Here's a simple approach:
Obtain binary image. We load the image, grayscale, Gaussian blur, then adaptive threshold.
Morphological operations. We create a rectangular kernel and morph open to remove the small noise
Find distorted rectangle contour and draw onto a mask. Find contours, determine rotated bounding box, and draw onto a blank mask
Find corners. We use the Shi-Tomasi Corner Detector already implemented as cv2.goodFeaturesToTrack which is supposedly shows better results compared to the Harris Corner Detector
Here's a visualization of each step:
Binary image
Morph open
Find rotated rectangle contour and draw/fill onto a blank mask
Draw rotated rectangle and corners to get result
Corner coordinates
(448.0, 337.0)
(164.0, 332.0)
(452.0, 123.0)
(168.0, 118.0)
Code
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, adaptive threshold
image = cv2.imread("1.png")
mask = np.zeros(image.shape, dtype=np.uint8)
gray = 255 - cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 51, 3)
# Morph open
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
# Find distorted rectangle contour and draw onto a mask
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
rect = cv2.minAreaRect(cnts[0])
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(36,255,12),2)
cv2.fillPoly(mask, [box], (255,255,255))
# Find corners on the mask
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
corners = cv2.goodFeaturesToTrack(mask, maxCorners=4, qualityLevel=0.5, minDistance=150)
for corner in corners:
x,y = corner.ravel()
cv2.circle(image,(x,y),8,(255,120,255),-1)
print("({}, {})".format(x,y))
cv2.imshow("thresh", thresh)
cv2.imshow("opening", opening)
cv2.imshow("mask", mask)
cv2.imshow("image", image)
cv2.waitKey(0)
You can try with an adaptive threshold. Then you may either use cornerHarris if you only need corners, or depending on what you need to do next, you could also find useful findContours, which returns a list of bounding boxes
I was able to locate 3 out of the 4 points, the 4th point can be found easily given the other three points since it's rectangle. Here is my solution:
import cv2
import numpy as np
img = cv2.imread('6dUIr.png',1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#smooth the image
kernel = np.ones((5,5),np.float32)/25
gray = cv2.filter2D(gray,-1,kernel)
#histogram equalization
clahe = cv2.createCLAHE(clipLimit=1.45, tileGridSize=(4,4))
cl1 = clahe.apply(gray)
#find edges
edges = cv2.Canny(cl1,4,100)
#find corners
dst = cv2.cornerHarris(edges,2,3,0.04)
#result is dilated for marking the corners, not important
dst = cv2.dilate(dst,None)
# Threshold for an optimal value, it may vary depending on the image.
img[dst>0.25*dst.max()]=[0,0,255]
cv2.imshow('edges', edges)
cv2.imshow('output', img)
# cv2.imshow('Histogram equalized', img_output)
cv2.waitKey(0)
The code has many hard coded thresholds but it's a good start.

Categories